Improving Chinese electronic medical record retrieval by field weight assignment, negation detection, and re-ranking.

The technique of information retrieval has been widely used in electronic medical record (EMR) systems. It's a pity that most existing methods have not considered the structures and language features of Chinese EMRs, which affects the performance of retrieval. To improve accuracy and comprehensiveness, we propose an improved algorithm of Chinese EMR retrieval. First, the weights of fields in Chinese EMRs are assigned based on the corresponding importance in clinical applications. Second, negative relations in EMRs are detected, and the retrieval scores of negative terms are adjusted accordingly. Third, the retrieval results are re-ranked by expansion terms and time information to enhance the recall without decreasing precision. Experiment results show that the improved algorithm increases the precision and recall significantly, which shows that the algorithm takes a full account of the characteristics of Chinese EMRs and fits the needs for clinical applications.

Structural annotation, semi-quantification and toxicity prediction of pyrrolizidine alkaloids from functional food: In silico and molecular networking strategy.

Many traditional Chinese herbs contain pyrrolizidine alkaloids (PAs), which have been reported to be toxic to livestock and humans. However, the lack of PAs standards makes it difficult to effectively conduct a risk assessment in the varied components of traditional Chinese medicine. It is necessary to propose a suitable strategy to obtain the representative occurrence data of PAs in complex systems. A comprehensive approach for annotating the structures, concentration, and mutagenicity of PAs in three Chinese herbs has been proposed in this article. First, feature-based molecular networking (FBMN) combined with network annotation propagation (NAP) on the Global Natural Products Social Molecular Networking web platform speeds up the process of annotating PAs found in Chinese herbs. Second, a semi-quantitative prediction model based on the quantitative structure and ionization intensity relationship (QSIIR) is used to forecast the amounts of PAs in complex substrates. Finally, the T.E.S.T. was used to provide predictions regarding the mutagenicity of annotated PAs. The goal of this study was to develop a strategy for combining the results of several computer models for PA screening to conduct a comprehensive analysis of PAs, which is a crucial step in risk assessment of unknown PAs in traditional Chinese herbal preparations.

Using machine learning models to classify stroke risk level based on national screening data.

With the character of high incidence, high prevalence and high mortality, stroke has brought a heavy burden to families and society in China. In 2009, the Ministry of Health of China launched the China national stroke screening and intervention program, which screens stroke risk factors and conducts high-risk population interventions for people aged over 40 years old all over China. In this program, stroke risk factors include hypertension, diabetes, dyslipidemia, atrial fibrillation, smoking, lack of exercise, apparently overweight or obese and family history of stroke. People with more than two risk factors or with a history of stroke or transient ischemic attack (TIA) are considered as high-risk. However, it is impossible for this criterion to classify stroke risk level for people with "unknown" values in the fields of risk factors. The missing of stroke risk levels results in reduced efficiency of stroke interventions and inaccuracies in the statistical results at the national level. In this paper, firstly, we construct the training set and test set and process the imbalanced training set based on oversampling and undersampling method. Then, we develop logistic regression model, decision tree model, neural network model and random forest model for stroke risk classification, and evaluate these models based on the recall and precision. The results show that the model based on random forest achieves best performance considering recall and precision. The models constructed in this paper can improve the screening efficiency and avoid unnecessary rescreening and intervention expenditures.

QRStream: A Secure and Convenient Method for Text Healthcare Data Transferring.

With the increasing of health awareness, the users become more and more interested in their daily health information and healthcare activities results from healthcare organizations. They always try to collect them together for better usage. Traditionally, the healthcare data is always delivered by paper format from the healthcare organizations, and it is not easy and convenient for data usage and management. They would have to translate these data on paper to digital version which would probably introduce mistakes into the data. It would be necessary if there is a secure and convenient method for electronic health data transferring between the users and the healthcare organizations. However, for the security and privacy problems, almost no healthcare organization provides a stable and full service for health data delivery. In this paper, we propose a secure and convenient method, QRStream, which splits original health data and loads them onto QR code frame streaming for the data transferring. The results shows that QRStream can transfer text health data smoothly with an acceptable performance, for example, transferring 10K data in 10 seconds.

Analysis of HL7 EHRS Functional Model and Suggested Applications in China.

HL7 electronic health record system (EHRS) functional model is an international standard which gives scientific instructions for EHRS design and implementation. It has the features of technological irrelevancy, requirement hierarchy and functional comprehensiveness. It is composed of overarching, care provision, care provision support, administrative support, population health support, record infrastructure and trusted infrastructure. This paper describes the functionalities of each section in detail. To apply this functional model, the history of Chinese health information system construction is reviewed and the weakness is analyzed as a basis. Then this paper gives suggestions on the construction of health information system in China: to enhance the functionality of healthcare systems, to enhance the information network function of regional health information network (RHIN), and to redesign the trust architecture of RHIN.

CrowdMapping: A Crowdsourcing-Based Terminology Mapping Method for Medical Data Standardization.

Standardized terminology is the prerequisite of data exchange in analysis of clinical processes. However, data from different electronic health record systems are based on idiosyncratic terminology systems, especially when the data is from different hospitals and healthcare organizations. Terminology standardization is necessary for the medical data analysis. We propose a crowdsourcing-based terminology mapping method, CrowdMapping, to standardize the terminology in medical data. CrowdMapping uses a confidential model to determine how terminologies are mapped to a standard system, like ICD-10. The model uses mappings from different health care organizations and evaluates the diversity of the mapping to determine a more sophisticated mapping rule. Further, the CrowdMapping model enables users to rate the mapping result and interact with the model evaluation. CrowdMapping is a work-in-progress system, we present initial results mapping terminologies.

Dual imaging-guided photothermal/photodynamic therapy using micelles.

We report a type of photosensitizer (PS)-loaded micelles integrating cyanine dye as potential theranostic micelles for precise anatomical tumor localization via dual photoacoustic (PA)/near-infrared fluorescent (NIRF) imaging modalities, and simultaneously superior cancer therapy via sequential synergistic photothermal therapy (PTT)/photodynamic therapy (PDT). The micelles exhibit enhanced photostability, cell internalization and tumor accumulation. The dual NIRF/PA imaging modalities of the micelles cause the high imaging contrast and spatial resolution of tumors, which provide precise anatomical localization of the tumor and its inner vasculature for guiding PTT/PDT treatments. Moreover, the micelles can generate severe photothermal damage on cancer cells and destabilization of the lysosomes upon PTT photoirradiation, which subsequently facilitate synergistic photodynamic injury via PS under PDT treatment. The sequential treatments of PTT/PDT trigger the enhanced cytoplasmic delivery of PS, which contributes to the synergistic anticancer efficacy of PS. Our strategy provides a dual-modal cancer imaging with high imaging contrast and spatial resolution, and subsequent therapeutic synergy of PTT/PDT for potential multimodal theranostic application.

Highly efficient hierarchical micelles integrating photothermal therapy and singlet oxygen-synergized chemotherapy for cancer eradication.

It is highly desirable to develop theranostic nanoparticles for achieving cancer imaging with enhanced contrast and simultaneously multimodal synergistic therapy. Herein, we report a theranostic micelle system hierarchically assembling cyanine dye (indocyanine green) and chemotherapeutic compound (doxorubicin) (I/D-Micelles) as a novel theranostic platform with high drug loading, good stability and enhanced cellular uptake via clathrin-mediated endocytosis. I/D-Micelles exhibit the multiple functionalities including near-infrared fluorescence (NIRF), hyperthermia and intracellular singlet oxygen from indocyanine green, and simultaneous cytotoxicity from doxorubicin. Upon photoirradiation, I/D-Micelles can induce NIRF imaging, acute photothermal therapy via hyperthermia and simultaneous synergistic chemotherapy via singlet oxygen-triggered disruption of lysosomal membranes, eventually leading to enhanced NIRF imaging and superior tumor eradication without any re-growth. Our results suggest that the hierarchical micelles can act as a superior theranostic platform for cancer imaging and multimodal synergistic therapy.

Micelles assembled with carbocyanine dyes for theranostic near-infrared fluorescent cancer imaging and photothermal therapy.

It is an emerging focus to explore a theranostic nanocarrier for simultaneous cancer imaging and therapy. Herein, we demonstrate a theranostic micelle system for cancer near infrared fluorescent (NIRF) imaging with enhanced signal to noise ratio and superior photothermal therapy. The copolymers consisting of monomethoxy poly(ethylene glycol) and alkylamine-grafted poly(L-aspartic acid) are assembled with carbocyanine dyes into theranostic micelles, which exhibit small size, high loading capacity, good stability, sustained release behavior, and enhanced cellular uptake. The micelles achieve the preferable biodistribution and long-term retention of carbocyanine dyes at tumor, which result in enhanced NIRF imaging by generating stable retention of NIRF signals at both hypervascular and hypovascular tumors during a long-term imaging period of up to 8 day, accompanying with negligible noise at normal tissues. The photostability of carbocyanine dye (Cypate) plays an important role for long-term cancer imaging with enhanced SNR. Moreover, the micelles exhibit severe photothermal damage on cancer cells via the destabilization of subcellular organelles upon photoirradiation, causing superior photothermal tumor regress. The micelles act as a powerful theranostic nanocarrier for simultaneous cancer imaging with high contrast and superior photothermal therapy.