Dataset Information

Syndrome Differentiation Analysis on Mars500 Data of Traditional Chinese Medicine.

ABSTRACT: Mars500 study was a psychological and physiological isolation experiment conducted by Russia, the European Space Agency, and China, in preparation for an unspecified future manned spaceflight to the planet Mars. Its intention was to yield valuable psychological and medical data on the effects of the planned long-term deep space mission. In this paper, we present data mining methods to mine medical data collected from the crew consisting of six spaceman volunteers. The synthesis of the four diagnostic methods of TCM, inspection, listening, inquiry, and palpation, is used in our syndrome differentiation. We adopt statistics method to describe the syndrome factor regular pattern of spaceman volunteers. Hybrid optimization based multilabel (HOML) is used as feature selection method and multilabel k-nearest neighbors (ML-KNN) is applied. According to the syndrome factor statistical result, we find that qi deficiency is a base syndrome pattern throughout the entire experiment process and, at the same time, there are different associated syndromes such as liver depression, spleen deficiency, dampness stagnancy, and yin deficiency, due to differences of individual situation. With feature selection, we screen out ten key factors which are essential to syndrome differentiation in TCM. The average precision of multilabel classification model reaches 80%.

SUBMITTER: Li YZ

PROVIDER: S-EPMC4606216 | biostudies-other | 2015

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:Objective: Vascular cognitive impairment (VCI) accounts for approximately 50%-70% of all dementia cases and poses a significant burden on existing medical systems. Identifying an optimal strategy for preventing VCI and developing efficient symptomatic treatments remains a significant challenge. Syndrome differentiation represents a fundamental approach for personalized diagnosis and treatment in Traditional Chinese Medicine (TCM) and aligns with the principles of precision medicine. The objective of this study was to elucidate the metabolic characteristics of VCI based on TCM syndrome differentiation, thus providing novel insights into the diagnosis and treatment of VCI. Methods: A 2-year cross-sectional cognitive survey was conducted in four communities in Beijing between September 2020 and November 2022. The syndrome differentiation of participants was based on the Kidney-Yang Deficiency Syndrome Scale (KYDSS), which was originally developed by Delphi expert consultation. The identification of serum metabolites was performed by Ultra performance liquid chromatography (UPLC) analysis coupled with an electrospray ionization quadruple time-of-flight mass spectrometer (ESI-QTOF MS). Multivariate, univariate, and pathway analyses were used to investigate metabolic changes. Logistic regression models were also used to construct metabolite panels that were capable of discerning distinct groups. Phospholipase A2 (PLA2) levels were measured by a commercial ELISA kit. Results: A total of 2,337 residents completed the survey, and the prevalence of VCI was 9.84%. Of the patients with VCI, those with Kidney-Yang deficiency syndrome (VCIS) accounted for 70.87% of cases and exhibited more severe cognitive impairments. A total of 80 participants were included in metabolomics study, including 30 with VCIS, 20 without Kidney-Yang deficiency syndrome (VCINS), and 30 healthy control participants (C). Ultimately, 45 differential metabolites were identified when comparing the VCIS group with group C, 65 differential metabolites between the VCINS group and group C, and 27 differential metabolites between the VCIS group and the VCINS group. The downregulation of phosphatidylethanolamine (PE), and phosphatidylcholine (PC) along with the upregulation of lysophosphatidylethanolamine (LPE), lysophosphatidylcholine (LPC), phosphatidic acid (PA) and phospholipase A2 (PLA2) can be considered as the general metabolic characteristics associated with VCI. Dysfunction of glycerophospholipids, particularly LPEs and PCs, was identified as a key metabolic characteristic of VCIS. In particular Glycerophospho-N-Arachidonoyl Ethanolamine (GP-NArE) was discovered for the first time in VCI patients and is considered to represent a potential biomarker for VCIS. The upregulation of PLA2 expression was implicated in the induction of alterations in glycerophospholipid metabolism in both VCIS and VCINS. Moreover, robust diagnostic models were established based on these metabolites, achieving high AUC values of 0.9322, 0.9550, and 0.9450, respectively. Conclusion: These findings contribute valuable information relating to the intricate relationship between metabolic disorders in VCI, neurodegeneration and vascular/neuroinflammation. Our findings also provide a TCM perspective for the precise diagnosis and treatment of VCI in the context of precision medicine.

Project description:BACKGROUND:Traditional Chinese medicine (TCM) has been shown to be an efficient mode to manage advanced lung cancer, and accurate syndrome differentiation is crucial to treatment. Documented evidence of TCM treatment cases and the progress of artificial intelligence technology are enabling the development of intelligent TCM syndrome differentiation models. This is expected to expand the benefits of TCM to lung cancer patients. OBJECTIVE:The objective of this work was to establish end-to-end TCM diagnostic models to imitate lung cancer syndrome differentiation. The proposed models used unstructured medical records as inputs to capitalize on data collected for practical TCM treatment cases by lung cancer experts. The resulting models were expected to be more efficient than approaches that leverage structured TCM datasets. METHODS:We approached lung cancer TCM syndrome differentiation as a multilabel text classification problem. First, entity representation was conducted with Bidirectional Encoder Representations from Transformers and conditional random fields models. Then, five deep learning-based text classification models were applied to the construction of a medical record multilabel classifier, during which two data augmentation strategies were adopted to address overfitting issues. Finally, a fusion model approach was used to elevate the performance of the models. RESULTS:The F1 score of the recurrent convolutional neural network (RCNN) model with augmentation was 0.8650, a 2.41% improvement over the unaugmented model. The Hamming loss for RCNN with augmentation was 0.0987, which is 1.8% lower than that of the same model without augmentation. Among the models, the text-hierarchical attention network (Text-HAN) model achieved the highest F1 scores of 0.8676 and 0.8751. The mean average precision for the word encoding-based RCNN was 10% higher than that of the character encoding-based representation. A fusion model of the text-convolutional neural network, text-recurrent neural network, and Text-HAN models achieved an F1 score of 0.8884, which showed the best performance among the models. CONCLUSIONS:Medical records could be used more productively by constructing end-to-end models to facilitate TCM diagnosis. With the aid of entity-level representation, data augmentation, and model fusion, deep learning-based multilabel classification approaches can better imitate TCM syndrome differentiation in complex cases such as advanced lung cancer.

Dataset Information

Syndrome Differentiation Analysis on Mars500 Data of Traditional Chinese Medicine.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets