Traditional Chinese medicine(TCM) decoction pieces are a core carrier for the inheritance and innovation of TCM, and their quality and safety are critical to public health and the sustainable development of the industry. Conventional quality control models, while having established a well-developed system through long-term practice, still face challenges such as relatively long inspection cycles, insufficient objectivity in characterizing complex traits, and urgent needs for improving the efficiency of integrating multidimensional quality information when confronted with the dual demands of large-scale production and precision quality control. With the rapid development of artificial intelligence, machine learning can deeply analyze multidimensional data of the morphology, spectroscopy, and chemical fingerprints of decoction pieces by constructing high-dimensional feature space analysis models, significantly improving the standardization level and decision-making efficiency of quality evaluation. This article reviews the research progress in the application of machine learning in the processing, production, and rapid quality evaluation of TCM decoction pieces. It further analyzes current challenges in technological implementation and proposes potential solutions, offering theoretical and technical references to advance the digital and intelligent transformation of the industry.
Machine Learning ; Drugs, Chinese Herbal/standards* ; Quality Control ; Medicine, Chinese Traditional/standards* ; Humans

The purpose of this study was to enrich the genomic information and provide a basis for further development and utilization of Polygonatum kingianum. The fresh rhizome of P. kingianum was used as the experimental material, and the full-length transcriptome was sequenced by PacBio Sequel platform. The final measured polymerase reads were 1 120 485, with a total of 77.73 GB of data. In NR database, 41 864 homologous sequence alignments were aligned to 5 species; 40 506 were annotated in the KOG database and classified into 26 categories based on their functionality; 69 060 GO annotated 32 functional groups divided into 3 categories: cellular components, molecular functions, and biological processes; 45 779 annotations were added to 145 metabolic pathways in the KEGG database. Among them, there are 127 identified transcripts related to polysaccharide synthesis in the glycolysis/gluconeogenesis metabolic pathway, 144 in the starch and sucrose metabolic pathway, 85 in the amino acid sugar and nucleotide sugar metabolic pathway, and 69 in the fructose and mannose metabolic pathway. In addition, 1 781 transcription factors were detected, distributed in 37 transcription factor families; 180 293 SSR loci were detected, among which single base repeats accounted for the most, accounting for 30.48% of all base repeats, and at least five base repeats, accounting for only 0.14% of single base repeats. The results of this study provide important data supporting for enriching the genomic information of P. kingianum and exploring its effective biosynthetic pathway.

Methods: From September 3, 2018, to March 23, 2024, participants with essential hypertension (receiving antihypertensive medication treatment, hypertension group) and normal blood pressure (control group) were recruited from the Cardiology Department of Shanghai Hospital of Traditional Chinese Medicine, the Coronary Care Unit of Shanghai Tenth People's Hospital, the Physical Examination Center of Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, and the Gaohang Community Health Service Center. This study employed the propensity score matching (PSM) method to reduce study participants selection bias. Spectral information in the facial visible light spectrum of the subjects was collected using a flame spectrometer, and the spectral chromaticity values were calculated using the equal-interval wavelength method. The study analyzed the differences in spectral reflectance across various facial regions, including the entire face, forehead, glabella, nose, jaw, left and right zygomatic regions, left and right cheek regions as well as differences in parameters within the Lab color space between the two subject groups. Feature selection was conducted using least absolute shrinkage and selection operator (LASSO) regression, followed by the application of various machine learning algorithms, including logistic regression (LR), support vector machine (SVM), random forest (RF), Naïve Bayes (NB), and eXtreme Gradient Boosting (XGB). The reduced-dimensional dataset was split in a 7 : 3 ratio to establish a classification and assessment model for facial coloration related to primary hypertension. Additionally, model fusion techniques were applied to enhance the predictive power. The performance of the models was evaluated using metrics including the area under the curve (AUC) and accuracy. Shapley Additive exPlanations (SHAP) was used to interpret the outcomes of the models. Results: A total of 114 participants were included in both hypertension and control groups. Reflectance analysis across the entire face and eight predefined areas revealed that the hypertensive group exhibited significantly higher reflectance of corresponding color light in the blue-violet region (P < 0.05) and a lower reflectance in the red region (P < 0.05) compared with control group. Analysis of Lab color space parameters across the entire face and eight predefined areas showed that hypertensive group had significantly lower a and b values than control group (P < 0.05). LASSO regression analysis identified a total of 18 facial color features that were highly correlated with hypertension, including the a values of the chin and the right cheek, the reflectance at 380 nm and at 780 nm of the forehead. The results of the multi-model classification showed that the RF classification model was the most effective, with an AUC of 0.74 and an accuracy of 0.77. The combined model of RF + LR + SVM outperformed a single model in their classification performance, achieving an AUC of 0.80 and an accuracy of 0.76. SHAP model visualization results indicated that the top three contributors to ideal prediction results based on the characteristics from the facial spectrum were the reflectance at 380 nm across the entire face and of the nose as well as the a value of the chin. Conclusion Within the same age group, patients with essential hypertension exhibited significant and regular changes in facial color and facial spectral reflectance parameters after the administration of antihypertensive drugs. Furthermore, facial reflectance indicators, such as the overall reflectance at 380 nm and the a value of the chin, could offer valuable references for clinically assessing the drug efficacy and health status of patients with essential hypertension.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objective: This study aims to overcome challenges in lumbar spine imaging, particularly lumbar spinal stenosis, by developing an automated segmentation model using advanced techniques. Traditional manual measurement and lesion detection methods are limited by subjectivity and inefficiency. The objective is to create an accurate and automated segmentation model that identifies anatomical structures in lumbar spine magnetic resonance imaging scans. Methods: Leveraging a dataset of 539 lumbar spinal stenosis patients, the study utilizes the residual U-Net for semantic segmentation in sagittal and axial lumbar spine magnetic resonance images. The model, trained to recognize specific tissue categories, employs a geometry algorithm for anatomical structure quantification. Validation metrics, like Intersection over Union (IOU) and Dice coefficients, validate the residual U-Net’s segmentation accuracy. A novel rotation matrix approach is introduced for detecting bulging discs, assessing dural sac compression, and measuring yellow ligament thickness. Results: The residual U-Net achieves high precision in segmenting lumbar spine structures, with mean IOU values ranging from 0.82 to 0.93 across various tissue categories and views. The automated quantification system provides measurements for intervertebral disc dimensions, dural sac diameter, yellow ligament thickness, and disc hydration. Consistency between training and testing datasets assures the robustness of automated measurements. Conclusion Automated lumbar spine segmentation with residual U-Net and deep learning exhibits high precision in identifying anatomical structures, facilitating efficient quantification in lumbar spinal stenosis cases. The introduction of a rotation matrix enhances lesion detection, promising improved diagnostic accuracy, and supporting treatment decisions for lumbar spinal stenosis patients.

Objective To investigate the correlation between qi stagnation and phlegm stasis syndrome in the young and middle-aged population and the detection rate of thyroid nodules.Methods The clinical data of those who participated in the questionnaire survey and took thyroid ultrasonography at Dongguan Hospital of Guangzhou University of Chinese Medicine from June 1 to December 1,2023 were collected.The clinical information covered age,gender,family history,body mass index(BMI),related symptoms,and ultrasonographic findings.And then the related data were statistically analyzed.Results(1)The clinical data of 196 cases were collected,of which 65 cases(33.16%)suffered from thyroid nodules,50 cases(25.51%)were differentiated as qi stagnation and phlegm stasis syndrome,53 cases(27.04%)had qi depression constitution of traditional Chinese medicine(TCM),55 cases(28.06%)had blood stasis constitution,and 48 cases(24.49%)had phlegm-dampness constitution.(2)The results of univariate analysis showed that the relevant factors for thyroid nodules included female,family history,qi stagnation and phlegm stasis syndrome,qi depression constitution,blood stasis constitution,phlegm-dampness constitution,dizziness and headache,neck stiffness,swallowing discomfort,lump on the surface of the body,dysmenorrhea and amenorrhea,tightness in the chest,distending pain in hypochondrium,depressed in spirits,emotional vulnerability,distending pain in breast,gloomy complexion,darkish lips,dark circles around the eyes,heaviness of the body,eyelid edema,and profuse sputum,and the differences were all statistically significant(P＜0.05 or P＜0.01).(3)Multivariate Logistic regression analysis was performed on the basis of univariate analysis,and the results showed that qi stagnation and phlegm stasis syndrome(OR:4.03,95%CI:1.85-8.77),phlegm-dampness constitution(OR:4.68,95%CI:2.06-10.63),and lump on the surface of the body(OR:2.97,95%CI:1.11-7.95)were the influencing factors for thyroid nodules.(4)A prediction model for detecting thyroid nodules was constructed:logit(P)=-1.607+1.39×qi stagnation and phlegm stasis syndrome(0 expressing absence,1 expressing presence)+1.54×phlegm-dampness constitution(0 expressing absence,1 expressing presence)+1.09×lump on the surface of the body(0 expressing absence,1 expressing presence).The model was evaluated by using the receiver operating characteristic(ROC)curve,and the area under the curve(AUC)was 0.75(95%CI:0.67-0.83,P＜0.001).Conclusion In the young and middle-aged population,qi stagnation and phlegm stasis are the risk factors for the detectable rate of thyroid nodules.The early identification,risk prediction and timely intervention for the population with qi stagnation and phlegm stasis will be helpful for the prevention and treatment of thyroid nodules.

Since Curcumae Radix decoction pieces have multiple sources, it is difficult to distinguish depending on traditional cha-racters, and the mixed use of multi-source Curcumae Radix will affect its clinical efficacy. Heracles Neo ultra-fast gas phase electronic nose was used in this study to quickly identify and analyze the odor components of 40 batches of Curcumae Radix samples from Sichuan, Zhejiang, and Guangxi. Based on the odor fingerprints established for Curcumae Radix decoction pieces of multiple sources, the odor components was identified and analyzed, and the chromatographic peaks were processed and analyzed to establish a rapid identification method. Principal component analysis(PCA), discriminant factor analysis(DFA), and soft independent modeling cluster analysis(SIMCA) were constructed for verification. At the same time, one-way analysis of variance(ANOVA) combined with variable importance in projection(VIP) was employed to screen out the odor components with P<0.05 and VIP>1, and 13 odor components such as β-caryophyllene and limonene were hypothesized as the odor differential markers of Curcumae Radix decoction pieces of diffe-rent sources. The results showed that Heracles Neo ultra-fast gas phase electronic nose can well analyze the odor characteristics and rapidly and accurately discriminate Curcumae Radix decoction pieces of different sources. It can be applied to the quality control(e.g., online detection) in the production of Curcumae Radix decoction pieces. This study provides a new method and idea for the rapid identification and quality control of Curcumae Radix decoction pieces.
Drugs, Chinese Herbal/analysis* ; Electronic Nose ; China ; Plant Roots/chemistry* ; Limonene/analysis* ; Chromatography, High Pressure Liquid