Exploration of Decision-Making Methods Based on Syndrome Differentiation by “Data-Knowledge” Dual-Driven Models： A Case Study of Gastric Precancerous State / 中医杂志

Data analysis models may assist the transmission of traditional Chinese medicine （TCM） experience and clinical diagnosis and treatment， and the possibility of constructing a “data-knowledge” dual-drive model was explored by taking gastric precancerous state as an example. Data-driven is to make clinical decisions around data analysis， and its syndrome-differentiation decision-making research relies on hidden structural models and partially observable Markov decision-making processes to identify the etiology of diseases， syndrome elements， evolution of pathogenesis， and syndrome differentiation protocols； knowledge-driven is to make use of data and information to promote decision-making and action processes， and its syndrome-differentiation decision-making research relies on convolutional neural networks to improve the accuracy of local disease identification and syndrome differentiation. The “data-knowledge” dual-driven model can make up for the shortcomings of single-drive numerical simulation accuracy， and achieve a balance between local disease identification and macroscopic syndrome differentiation. On the basis of previous research， we explored the construction method of diagnostic assisted decision-making platform for gastric precancerous state， and believed that the diagnostic and decision-making ability of doctors can be extended through the assistance of machines and algorithms. Meanwhile， the related research methods were integrated and the core features of gastric precancerous state based on TCM syndrome differentiation and endoscopic pathology diagnosis and prediction were obtained， and the elements of endoscopic pathology recognition based on TCM syndrome differentiation were explored， so as to provide ideas for the in-depth research and innovative application of cutting-edge data analysis technology in the field of intelligent TCM syndrome differentiation.

Application progress on data-driven technologies in intelligent manufacturing of traditional Chinese medicine extraction / 中国中药杂志

The application of new-generation information technologies such as big data, the internet of things(IoT), and cloud computing in the traditional Chinese medicine(TCM)manufacturing industry is gradually deepening, driving the intelligent transformation and upgrading of the TCM industry. At the current stage, there are challenges in understanding the extraction process and its mechanisms in TCM. Online detection technology faces difficulties in making breakthroughs, and data throughout the entire production process is scattered, lacking valuable mining and utilization, which significantly hinders the intelligent upgrading of the TCM industry. Applying data-driven technologies in the process of TCM extraction can enhance the understanding of the extraction process, achieve precise control, and effectively improve the quality of TCM products. This article analyzed the technological bottlenecks in the production process of TCM extraction, summarized commonly used data-driven algorithms in the research and production control of extraction processes, and reviewed the progress in the application of data-driven technologies in the following five aspects: mechanism analysis of the extraction process, process development and optimization, online detection, process control, and production management. This article is expected to provide references for optimizing the extraction process and intelligent production of TCM.

Data-driven engineering framework with AI algorithm of Ginkgo Folium tablets manufacturing

Smart manufacturing still remains critical challenges for pharmaceutical manufacturing. Here, an original data-driven engineering framework was proposed to tackle the challenges. Firstly, from sporadic indicators to five kinds of systematic quality characteristics, nearly 2,000,000 real-world data points were successively characterized from Ginkgo Folium tablet manufacturing. Then, from simplex to the multivariate system, the digital process capability diagnosis strategy was proposed by multivariate Cpk integrated Bootstrap-t. The Cpk of Ginkgo Folium extracts, granules, and tablets were discovered, which was 0.59, 0.42, and 0.78, respectively, indicating a relatively weak process capability, especially in granulating. Furthermore, the quality traceability was discovered from unit to end-to-end analysis, which decreased from 2.17 to 1.73. This further proved that attention should be paid to granulating to improve the quality characteristic. In conclusion, this paper provided a data-driven engineering strategy empowering industrial innovation to face the challenge of smart pharmaceutical manufacturing.

Research on data-driven precision management mode for chronic diseases / 中华医院管理杂志

Chronic diseases have grown into a major public health threat affecting social development. The traditional management of chronic diseases tends to characterize " prioritizing treatment and neglecting prevention" . In this study, big data application, knowledge management, knowledge service and other theories and methods in the information management discipline were put in practice of chronic disease management. Thanks to the construction of a multi-source and heterogeneous chronic disease database, a chronic disease health knowledge analysis platform and a chronic disease service application platform, the following objectives were achieved. These included the data interconnections between patients′ self-testing data and medical institutions′ data in chronic disease data management, the integration and accurate delivery of chronic disease health knowledge, and personalized and accurate services covering the whole process of chronic disease management, namely prevention, diagnosis, treatment and rehabilitation.Since August 2019, this management mode has been used to build a diabetes big data platform. By January 2022, 380 million pieces of diagnosis, treatment and management data were collected from about 2.16 million residents, with the accuracy rate of 97.46% and the integrity rate of 96.07%. Corresponding knowledge base and service platform were built, and personalized service was provided to diabetes patients. These measures improvd the awareness rate, treatment rate, treatment control rate, science popularization and communication rate covering both diabetes patients and community residents.

Data-driven based four examinations in TCM: a survey / 数字中医药（英文）

@#Traditional Chinese medicine (TCM) diagnosis is a unique disease diagnosis method with thousands of years of TCM theory and effective experience. Its thinking mode in the process is different from that of modern medicine, which includes the essence of TCM theory. From the perspective of clinical application, the four diagnostic methods of TCM, including inspection, auscultation and olfaction, inquiry, and palpation, have been widely accepted by TCM practitioners worldwide. With the rise of artificial intelligence (AI) over the past decades, AI based TCM diagnosis has also grown rapidly, marked by the emerging of a large number of data-driven deep learning models. In this paper, our aim is to simply but systematically review the development of the data-driven technologies applied to the four diagnostic approaches, i.e. the four examinations, in TCM, including data sets, digital signal acquisition devices, and learning based computational algorithms, to better analyze the development of AI-based TCM diagnosis, and provide references for new research and its applications in TCM settings in the future.

Comparative study on composition regularities of Chinese materia medica formulas for four kinds of emmeniopathies by data-driven approach / 中草药

To study and compare the composition regularities of Chinese materia medica (CMM) formulas for four kinds of emmeniopathies, including irregular menstruation, dysmenorrhea, amenorrhea, and uterine bleeding, and contribute to the interpretation and prescription of composition mechanism for the optimization of CMM formulas by using a data-driven approach. A total of 1 761 CMM formulas from the Dictionary of Chinese Medicine Prescription for emmeniopathies were analyzed by the data mining method of Apriori algorithm with the indicators of support, confidence, and lift. The frequencies, composition regularities, and pivotal compositions of CMM were analyzed comparatively. Angelicae Sinensis Radix (ASR), Chuanxiong Rhizoma (CR), CR-ASR, Paeoniae Radix Alba (PRA)-ASR, and PRA-CR-ASR were higher commonly used CMM and CMM combinations for all the four emmeniopathies. Astragali Radix was the highest frequently used CMM for uterine bleeding. Persicae Semen (PS), Rhei Radix et Rhizoma, and PS-ASR were the frequently used CMM and CMM combinations for amenorrhea. Cyperi Rhizoma and Cyperi Rhizoma-ASR were the frequently used CMM and CMM combinations for dysmenorrhea. The latent association rules with significant lift included Hirudo→Tabanus and Olibanum→Myrrha for irregular menstruation, and Sappan Lignum→Carthami Flos and Tabanus→Hirudo for amenorrhea. Based on the CMM formulas from the Dictionary of Chinese Medicine Prescription, the data-driven approach revealed the similarities and differences in CMM compositions for the four emmeniopathies and uncovered the latent composition regularities and the pivotal CMM effectively.

TICA: Transcriptional Interaction and Coregulation Analyzer / 基因组蛋白质组与生物信息学报·英文版

Transcriptional regulation is critical to cellular processes of all organisms. Regulatory mechanisms often involve more than one transcription factor (TF) from different families, binding together and attaching to the DNA as a single complex. However, only a fraction of the regulatory partners of each TF is currently known. In this paper, we present the Transcriptional Interaction and Coregulation Analyzer (TICA), a novel methodology for predicting heterotypic physical interaction of TFs. TICA employs a data-driven approach to infer interaction phenomena from chromatin immunoprecipitation and sequencing (ChIP-seq) data. Its prediction rules are based on the distribution of minimal distance couples of paired binding sites belonging to different TFs which are located closest to each other in promoter regions. Notably, TICA uses only binding site information from input ChIP-seq experiments, bypassing the need to do motif calling on sequencing data. We present our method and test it on ENCODE ChIP-seq datasets, using three cell lines as reference including HepG2, GM12878, and K562. TICA positive predictions on ENCODE ChIP-seq data are strongly enriched when compared to protein complex (CORUM) and functional interaction (BioGRID) databases. We also compare TICA against both motif/ChIP-seq based methods for physical TF-TF interaction prediction and published literature. Based on our results, TICA offers significant specificity (average 0.902) while maintaining a good recall (average 0.284) with respect to CORUM, providing a novel technique for fast analysis of regulatory effect in cell lines. Furthermore, predictions by TICA are complementary to other methods for TF-TF interaction prediction (in particular, TACO and CENTDIST). Thus, combined application of these prediction tools results in much improved sensitivity in detecting TF-TF interactions compared to TICA alone (sensitivity of 0.526 when combining TICA with TACO and 0.585 when combining with CENTDIST) with little compromise in specificity (specificity 0.760 when combining with TACO and 0.643 with CENTDIST). TICA is publicly available at http://geco.deib.polimi.it/tica/.

The exposome and the future of epidemiology: a vision and prospect

It is widely accepted that a relatively small proportion of chronic disease can be explained by genetic factors alone. Although information about environmental exposure is important to comprehensively evaluate chronic diseases, this information is not sufficiently or accurately assessed by comparison with genomic factors. To emphasize the importance of more complete evaluation of environmental exposure, the concept of the exposome, which indicates the entirety of environmental exposure from conception onwards, was introduced in 2005. Since the 2010s several epidemiological studies, such as the Human Early-Life Exposome project, have applied the exposome concept. The exposome consists of three overlapping domains: the general external, the specific external, and the internal environments. General external factors include the broader socioeconomic environment, and specific external factors include lifestyles, occupations, and pollutant exposures. Internal factors include biological effects and responses. Because the exposome covers exposures from conception to death, the birth cohort is an important part of the exposome study. Although there is not yet an established consensus in selecting what, when, and where to measure concerning the exposome, the use of omics analyses, especially analysis of the metabolome, should be considered in order to implement the exposome concept in the birth cohort. The exposome needs to be measured repeatedly in certain important phases of life, such as during pregnancy and infancy. To perform exposome-informed epidemiological studies, untargeted data-driven approaches in conjunction with dimension reduction techniques need to be developed and refined. The exposome concept has the potential to make a breakthrough in overcoming some of the limitations of conventional epidemiology. Concerted national and international efforts are required for future exposome studies.

Research situation and expectation of clinical healthcare big data / 医疗卫生装备

Objective To cxplore the research and application of big data mining technology in clinical healthcare environment.Methods The characteristics of clinical heahhcare data mining methods were expounded and the current research status of healthcare data mining technology was analyzed in clinical task according to the literature mining.Meanwhile,the application of healthcare data mining in clinical environment was introduced from the following four aspects:medicine research,personalized diagnosis,risk prediction and process mining.Results The necessity and importance of research and application of clinical healthcare data mining were illustrated.Moreover,the achicvements of healthcare data mining in clinical application,as well as existing problems and technical difficulties were summarized.Furthermore,the development tendencies of healthcare data mining were predicted.Conclusion The research and application of clinical healthcare data mining have improved the healthcare quality and promoted the medical advances,which is the developmcnt direction of clinical healthcare research.

Methods of analysis based on the signal characteristics of fMRI / 国际生物医学工程杂志

The principles, traits, and proceedings of the data-driven methods including principal component analysis, independent component analysis and canonical analysis are summarized. And the aspects of the methods adapted to functional magnetic resonance images(fMRI) data are emphasized.