Medical Big Data Research Articles

Real-time autOmatically updated data warehOuse in healThcare (ROOT): an innovative and automated data collection system.

BackgroundThe American Society for Clinical Oncology recently launched the minimal common oncology data elements project to facilitate cancer data interoperability. However, clinical data are often unrecorded in an organized way, and converting them into a structured format can be time-consuming. Clinical Data Warehouse (CDW) is a database that consolidates data from different clinical sources. However, the clinical data extracted from this database include not only structured data but also natural language generated during clinical practice. Therefore, applying these data to a clinical study is challenging because they are unstructured, and unformatted to allow essential content to be found. This study determined how best to organize a huge amount of clinical data to evaluate the upper aerodigestive tract cancers’ clinical features and outcomes, including cancer of the head and neck, esophagus, lung, thymus, and mesothelioma.MethodsThe Real-time autOmatically updated data warehOuse in healThcare (ROOT) uses six main regions to describe the journey of cancer patients. This study, developed an algorithm optimized for each disease category using natural language processing of unstructured data and data capture of structured data. Data from patients diagnosed at the Samsung Medical Center from 2008–2020 were used.ResultsComprehensive clinical data for 67,617 patients across six tumor types: 28,954 with non-small-cell lung cancer, 2,540 with small-cell lung cancer, 30,035 with head and neck cancer, 4,950 with esophageal cancer, 966 with thymic cancer, and 172 with mesothelioma were collected. Additionally, the results of a longitudinal molecular study, including epidermal growth factor receptor (EGFR) mutations, anaplastic lymphoma kinase (ALK) tests, and next-generation sequencing (NGS), were included. Scattered information was integrated and automatically built up to match the cohort, allowing users to capture the most updated test results and treatment outcomes.ConclusionsThis landmark study documented the successful construction of a real-time updating system for medical big data, based on the CDW program.

An Efficient, Ensemble-Based Classification Framework for Big Medical Data.

Fetching useful information from big medical datasets is a complicated task in the big data age. Various classification algorithms are used in the data mining process to analyze information from the big medical dataset. Nevertheless, these classification algorithms are insufficient to handle big medical data. This work proposes an efficient, ensemble-based classification framework for big medical data to deal with this problem. The proposed work involves initially applying the preprocessing technique to remove noise, missing values, and unwanted features from big medical data. The process selects a subset of classifiers from a pool of classifiers. The selected classifiers are combined to form a hybrid system for efficient classification. The methodology further involves incremental learning from data samples, explaining the predicted outputs, and achieving high classification performance. Java is used for simulation, and the Cleveland Heart Disease big dataset and Diabetes big dataset are used for classification. The experimental result shows that the proposed ensemble algorithm provides an efficient classification compared with existing algorithms based on accuracy, precision, F-measure, recall, and execution time.

Research on the application of intelligent speech recognition technology in medical big data fog computing system

ABSTRACT Through the establishment of a voice database and voice recognition model, combined with voice recognition processing methods, an intelligent voice recognition input system with medical big data and fog computing as the scene is developed to realise the application of intelligent voice recognition technology in the system, which can reduce the medical staffdaily burden, reduce repetitive workload, and improve the quality and efficiency of clinical work. Based on the key technologies of intelligent voice recognition and medical big data, combined with the characteristics of fog computing, the development of electronic medical records and examination reports intelligent voice entry, mobile nursing intelligent voice entry, non-contact intelligent voice data interaction system, through the construction of fog computing model, design and develop an intelligent medical system to realise the rapid input and output of medical records and examination reports, reduce the workload of doctors and nurses, and concentrate their limited time on the treatment process itself. At the same time, according to the working characteristics of different medical departments, the intelligent system design adopts convenient, practical and efficient intelligent speech recognition technology application tools, and makes full use of big data technology and fog computing architecture to improve speech recognition rate, reduce network delay, and improve query efficiency, It is beneficial to assist the work of various clinical departments, better improve the treatment effect and innovate new medical models.

Analysis of the Effect of Emergency Ventilators on the Treatment of Critical Illness Based on Smart Medical Big Data.

Respiratory failure refers to pulmonary ventilation and ventilatory dysfunction caused by various reasons, which makes the patient unable to maintain the gas exchange required for stillness and causes a series of pathophysiological changes and corresponding clinical manifestations. In order to solve the problem of respiratory failure in critically ill patients, it is of great significance to analyze the role of microprocessor-based emergency ventilator in the treatment of critically ill patients. This article aims to study the role of microprocessor-based emergency ventilator in the treatment of critically ill patients. This paper presents the key technology based on the ARM11 processor. A breathing motion model is detected and established through a ventilator. The research objects are mainly divided into group A and group B. By comparing the two groups of emergency ventilator ventilation, it can effectively prevent the increase in respiratory muscle fatigue, reduce oxygen consumption, improve the patient's ventilation function and oxygen balance, quickly correct hypoxia and carbon dioxide storage, cooperate with drug treatment, and quickly take out the ventilator after relief. Good treatment results were achieved. The results show that the emergency ventilator controlled by a microcomputer is effective. The total effective rate of the control group was 71.11%, which was significantly lower than that of the observation group (86.67%).

Machine learning models of ischemia/hemorrhage in moyamoya disease and analysis of its risk factors

ObjectThis study aimed to determine the risk factors of ischemic/hemorrhagic stroke in patients suffering moyamoya disease (MMD), as well as to compare the effects of six analysis methods. MethodsIn the present retrospective study, the data originated from the database of Jiang Xi Province Medical Big Data Engineering & Technology Research Center. In addition, the information of patients with MMD that were admitted to the second affiliated hospital of Nanchang university from January 1st, 2012 to December 31st, 2019 was acquired. Six different machine learning methods were adopted to build the models, and XGboost, Logistic regression (LR) and Support vector machine (SVM) models were adopted to determine the risk factors of ischemic/hemorrhagic stroke in patients with MMD because of their excellent performance. Next, the effects of the built models were compared and validated in internal and independent external validation sets. The external validation set involving 204 cases from January 1st, 2018 to December 31st, 2019. ResultOn the whole, 790 patients with MMD were screened, i.e., 397 patients with cerebral infarction and 393 patients with cerebral hemorrhage. In the internal validation set, XGboost model exhibited significant discrimination (AUC>0.75), with its area under the curve (AUC) reaching 0.874 (95% CI: 0.859, 0.889). Compared with the LR and SVM models, the XGboost model in the internal validation set achieved the improved accuracy by 3.2% and 3.1%, respectively, whereas no significant difference was identified. ConclusionXGboost model could be more efficient in analyzing the risk factors of ischemic/hemorrhagic stroke in patients with MMD; the risk factors of hemorrhagic stroke in MMD might be closely related to Suzuki stages, presence of an aneurysm, rural residence, hospitalization times and age of onset.

Electronic medical record-based deep data cleaning and phenotyping improve the diagnostic validity and mortality assessment of infective endocarditis: medical big data initiative of CMUH.

BackgroundInternational Classification of Diseases (ICD) code–based claims databases are often used to study infective endocarditis (IE). However, the quality of ICD coding can influence the reliability of IE research. The impact of complementing the ICD-only approach with data extracted from electronic medical records (EMRs) has yet to be explored.MethodsWe selected the information of adult patients with discharge ICD codes for IE (ICD-9: 421, 112.81, 036.42, 098.84, 115.04, 115.14, 115.94, 424.9; ICD-10: I33, I38, I39) during 2005–2016 in China Medical University Hospital. Data extraction was conducted on the basis of the modified Duke criteria to establish a reference group comprising patients with definite or possible IE. Clinical characteristics and in-hospital mortality were compared between ICD-identified and Duke-confirmed cases. The positive predictive value (PPV) was used to quantify the IE identification performance of various phenotyping algorithms.ResultsA total of 593 patients with discharge ICD codes for IE were identified, only 56.7% met the modified Duke criteria. The crude in-hospital mortality for Duke-confirmed and Duke-rejected IE were 24.4% and 8.2%, respectively. The adjusted in-hospital mortality for ICD-identified IE was lower than that for Duke-confirmed IE by a difference of 5.1%. The best PPV was achieved (0.90, 95% CI 0.86–0.93) when major components of the Duke criteria (positive blood culture and vegetation) were integrated with ICD codes.ConclusionIntegrating EMR data can considerably improve the accuracy of ICD-only approaches in phenotyping IE, which can improve the validity of EMR-based studies and their applications, including real-time surveillance and clinical decision support.

Medical big data intrusion detection system based on virtual data analysis from assurance perspective

Medical big data intrusion detection system based on virtual data analysis from assurance perspective

Gaussian relevance vector MapReduce-based annealed Glowworm optimization for big medical data scheduling

Various big-data analytics tools and techniques have been developed for handling massive amounts of data in the healthcare sector. However, scheduling is a significant problem to be solved in smart healthcare applications to provide better quality healthcare services and improve the efficiency of related processes when considering large medical files. For this purpose, a new hybrid model called Gaussian Relevance Vector MapReduce-based Annealed Glowworm Optimization Scheduling (GRVM-AGS) was designed to improve the balancing of large medical data files between different physicians with higher scheduling efficiency and minimal time. First, a GRVM model was developed for the predictive analysis of input medical data. This model reduces the storage complexity of large medical data analysis by means of eliminating unwanted patient information and predicts the disease class with help of a Gaussian kernel function. Afterwards, GRVM performs AGS to schedule the efficient workloads among multiple datacenters based on the luciferin value in the smart healthcare environment with reduced scheduling time. Through computational experiments, we demonstrate that GRVM-AGS increases the scheduling efficiency and reduces the scheduling time of large medical data analysis compared to state-of-the-art approaches.

Clinical Acupoint Selection for the Treatment of Functional Constipation by Massage and Acupuncture Based on Smart Medical Big Data Analysis.

With the development of society and economy, people's lifestyle and eating habits have undergone great changes, such as spending a long time behind desks, sitting for a long time, drinking and staying up late, and emotional depression; functional constipation, a disease of the digestive system, has changed. It is extremely common, and the age of onset is gradually decreasing. The development of the medical and health industry is also accompanied by the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, which penetrates into all aspects of the medical and health field and has entered the stage of smart medical care. This article proposes a study on the clinical acupoint selection rules of massage and acupuncture treatment of functional constipation based on smart medical big data analysis. This article adopts a variety of methods such as literature data method and experimental research method to carry out related theoretical research and promotion of massage and acupuncture treatment under the background of smart medical big data and design a clinical experiment of massage and acupuncture treatment based on big data analysis for functional constipation. The advantages of big data algorithms, the law of selecting acupoints in massage and acupuncture treatment, and the comparison of CCS symptom score and PAC-QOL score are analyzed. From the frequency of acupuncture treatment of functional constipation, the top 5 acupoints are Tianshu, Shangjuxu, Dachangshu, Zusanli, and Zhigou. In this paper, the total effective rate of treatment in the experimental group reached 96.56%, while the total effective rate of treatment in the control group was only 75.02%. Tuina and acupuncture treatment of functional constipation has a good therapeutic effect and is worthy of extensive clinical application.

Research on the Construction and Application of Breast Cancer-Specific Database System Based on Full Data Lifecycle.

Relying on the Biomedical Big Data Center of West China Hospital, this paper makes an in-depth research on the construction method and application of breast cancer-specific database system based on full data lifecycle, including the establishment of data standards, data fusion and governance, multi-modal knowledge graph, data security sharing and value application of breast cancer-specific database. The research was developed by establishing the breast cancer master data and metadata standards, then collecting, mapping and governing the structured and unstructured clinical data, and parsing and processing the electronic medical records with NLP natural language processing method or other applicable methods, as well as constructing the breast cancer-specific database system to support the application of data in clinical practices, scientific research, and teaching in hospitals, giving full play to the value of medical big data of the Biomedical Big Data Center of West China Hospital.

Medical big data for smart healthcare

As most people expect, the COVID-19 pandemic will change our life radically. One of the directions is expected to minimize off-line contacts in daily lives and healthcare is surely not the exception. Big hospitals, which are centralized systems evolved to deliver healthcare most effectively, can become the media of the spread of diseases in some cases and the adoption of a decentralized healthcare system will be a helpful strategy to prevent it. This strategy can be implemented through a smart healthcare system, and it will be one more necessity of a smart healthcare system in our society. Smart healthcare, which will be delivered mainly through online contact, is a very comprehensive concept enabling otherwise not possible healthcare such as health monitoring using life-log data from the wearable device and far beyond the online consultation with a doctor. Although there will be many social, ethical, and technical challenges for smart healthcare, the discussion today will be limited to two challenges, interoperability and protecting the data subjects' rights. Smart healthcare needs to collect and process comprehensive health information from a vast number of data subjects during its development and delivery and the data subjects' rights are highly vulnerable during these processes. Collecting and exchanging health information from various sources such as hospitals, clinics, smartwatches, and so on, inevitably raises the issue of interoperability of the data from different sources. The implementation of smart healthcare requires technical solutions to both challenges. General Data Protection Regulation, recently issued by the EU, deals the data subjects' rights very seriously, such as the right to be informed, the right of access, the right to rectification, the right to erasure, the right to restrict processing, the right to data portability, the right to object, and the rights in relation to automated decision making and profiling. Technical innovations required to protect these data subjects' rights will be discussed here. Compared to traditional healthcare which mostly dealt with medical data generated within the healthcare facility itself, smart healthcare requires health data beyond the healthcare facilities. Not to mention the life-log data from different wearable devices, even the medical data from different hospitals are not interoperable. Although many health information standards have been proposed, such as Systematized Nomenclature of Medicine Clinical Terms (SMOMED CT), Logical Observation Identifier Name Code (LOINC), Health Level 7 Fast Healthcare Interoperability Resources (HL7 FHIR), and so on, the adoption of these standards in hospital information system in Korea has been very slow. This low adoption of health information standards in our hospital information system obstructs the so-called, meaningful use of electronic medical records. The necessity of adopting health information standards will be refreshed today. Smart healthcare requires the active participation of health consumers and active participation of health consumers requires their health literacy. Health literacy of health consumers will be fostered by innovative technical aids such as data visualization, the decision support system for consumers, and more. Health literacy will the most powerful driving force of smart healthcare implementation.

A visualization algorithm for medical big data based on deep learning

This paper proposes a visualization algorithm model based on deep learning. First, through entity link disambiguation and knowledge map embedding and extraction, the structured disease knowledge in the medical knowledge map is obtained, and the disease feature word vector and the corresponding knowledge entity vector in the disease description text are used as the multi-channel input of Convolutional Neural Networks (CNN). Second, in the convolution process, different types of diseases are represented from two levels of semantics and knowledge. Finally, through training and testing on multiple types of disease description text data sets. The experimental results show that the sensitivity of the method is 0.94, and the accuracy rate reaches 0.87, which verifies that this method of joint training of knowledge and data is more suitable for the initial diagnosis of the disease type described by the condition.

Veterinary Big Data: When Data Goes to the Dogs

Dogs provide an ideal model for study as they have the most phenotypic diversity and known naturally occurring diseases of all non-human land mammals. Thus, data related to dog health present many opportunities to discover insights into health and disease outcomes. Here, we describe several sources of veterinary medical big data that can be used in research. These sources include medical records from primary medical care centers or referral hospitals, medical claims data from animal insurance companies, and datasets constructed specifically for research purposes. No data source provides information that is without limitations, but large-scale, prospective, longitudinally collected data from dog populations are ideal for further research as they offer many advantages over other data sources.

Design and Application of Perioperative Multi-center Data Center

Based on 18 hospitals including the Chinese People's Liberation Army General Hospital and Peking University People's Hospital, and based on the "Specifications for Perioperative Data", explore the construction and application of perioperative multi-center data centers in the era of medical big data. The use of data ferry technology avoids hidden safety hazards in hospitals, realizes the integration and sharing of perioperative medical data of various medical institutions, and forms a complete data chain combining patient medical data and follow-up data.

A differential privacy protection query language for medical data: a proof-of-concept system validation

Abstract Objective: Medical data mining and sharing is an important process in E-Health applications. However, because these data consist of a large amount of personal private information of patients, there is the risk of privacy disclosure when sharing and mining. Therefore, ensuring the security of medical big data in the process of publishing, sharing, and mining has become the focus of current research. The objective of our study is to design a framework based on a differential privacy protection mechanism to ensure the secure sharing of medical data. We developed a privacy protection query language (PQL) that integrates multiple data mining methods and provides a secure sharing function. Methods: This study is mainly performed in Xuzhou Medical University, China and designs three sub-modules: a parsing module, mining module, and noising module. Each module encapsulates different computing methods, such as a composite parser and a noise theory. In the PQL framework, we apply the differential privacy theory to the results of the computing between modules to guarantee the security of various mining algorithms. These computing devices operate independently, but the mining results depend on their cooperation. In addition, PQL is encapsulated in MNSSp3 that is a data mining and security sharing platform and the data comes from public data sets, such as UCBI. The public data set (NCBI database) was used as the experimental data, and the data collection time was January 2020. Results: We designed and developed a query language that provides functions for medical data mining, sharing, and privacy preservation. We theoretically proved the performance of the PQL framework. The experimental results show that the PQL framework can ensure the security of each mining result and the availability of the output results is above 97%. Conclusion: Our framework enables medical data providers to securely share health data or treatment data and develops a usable query language, based on a differential privacy mechanism, that enables researchers to mine information securely using data mining algorithms.

The Function and Prognostic Value of RNA-Binding Proteins in Colorectal Adenocarcinoma Were Analyzed Based on Bioinformatics of Smart Medical Big Data.

Colon cancer is the third most frequent cancer in the world and is mainly adenocarcinoma in terms of pathological type. It has been confirmed that the dysregulation of RNA-binding proteins (RBPs) significantly participates in the occurrence and development of numerous malignant tumors. Therefore, we analyzed the RBPs associated with colon adenocarcinoma (COAD) to assess their possible biological effects and prognostic value. A total of 398 COAD tissue datasets and 39 normal tissue datasets were retrieved from the TCGA data resource and screened out the RBPs, which are differentially expressed between tumor tissues and nontumor tissues. Then, bioinformatics analyses based on smart medical big data were conducted on these RBPs. Overall, 181 differentially expressed RBPs were uncovered, consisting of 121 upregulated RBPs and 60 downregulated RBPs. Finally, we selected 7 prognostic-related RBPs with research prospects and constructed a prognostic model according to the median risk score. There were remarkable differences in OS between the high-risk and low-risk groups. In addition, the performance of the prognostic model was evaluated and verified with other COAD patient data in the TCGA database. The results showed that the area under the ROC curve (AUC) for the train group was 0.744 and the one for the test group was 0.661, confirming that the model assesses patients' prognosis to some extent. And based on 7 hub RBPs, we constructed a nomogram as a reference for evaluating the survival rate of COAD patients.

Effects of 5-HT₃ receptor antagonists on cisplatin-induced kidney injury.

Nausea, vomiting, and renal injury are the common adverse effects associated with cisplatin. Cisplatin is excreted via the multidrug and toxin release (MATE) transporter, and the involvement of the MATE transporter in cisplatin‐induced kidney injury has been reported. The MATE transporter is also involved in the excretion of ondansetron, but the effects of 5‐HT3 receptor antagonists used clinically for cisplatin‐induced renal injury have not been elucidated. Therefore, the aim of this study was to investigate the effects of 5‐HT3 receptor antagonists in a mouse model of cisplatin‐induced kidney injury and to validate the results using medical big data analysis of more than 1.4 million reports and a survey of 3000 hospital medical records. The concomitant use of a first‐generation 5‐HT3 receptor antagonist (ondansetron, granisetron, or ramosetron) significantly increased cisplatin accumulation in the kidneys and worsened renal damage. Conversely, the concomitant use of palonosetron had no effect on renal function compared with the use of cisplatin alone. Furthermore, an analysis of data from the US Food and Drug Administration Adverse Event Reporting System and retrospective medical records revealed that the combination treatment of cisplatin and a first‐generation 5‐HT3 receptor antagonist significantly increased the number of reported renal adverse events compared with the combination treatment of cisplatin and a second‐generation 5‐HT3 receptor antagonist. These results suggest that compared with the first‐generation antagonists, second‐generation 5‐HT3 receptor antagonists do not worsen cisplatin‐induced acute kidney injury. The findings should be validated in a prospective controlled trial before implementation in clinical practice.

Research on Diagnostic Information of Smart Medical Care Based on Big Data.

The medical field has gradually become intelligent, and information and the research of intelligent medical diagnosis information have received extensive attention in the medical field. In response to this situation, this paper proposes a Hadoop-based medical big data processing system. The system first realized the ETL module based on Sqoop and the transmission function of unstructured data and then realized the distributed storage management function based on HDFS. Finally, a MapReduce algorithm with variable key values is proposed in the data statistical analysis module. Through simulation experiments on the system modules and each algorithm, the results show that because the traditional nondistributed big data acquisition module transmits the same scale of data, it consumes more than 3200 s and the transmission time exceeds 3000 s. The time consumption of smart medical care under the 6G protocol is 150 s, the transmission time is 146 s, and the time is reduced to 1/10 of the original. The research of intelligent medical diagnosis information based on big data has good rationality and feasibility.

Legal Governance of Brain Data Derived from Artificial Intelligence

Legal Governance of Brain Data Derived from Artificial Intelligence

Deep Learning Methods for Heart Sounds Classification: A Systematic Review.

The automated classification of heart sounds plays a significant role in the diagnosis of cardiovascular diseases (CVDs). With the recent introduction of medical big data and artificial intelligence technology, there has been an increased focus on the development of deep learning approaches for heart sound classification. However, despite significant achievements in this field, there are still limitations due to insufficient data, inefficient training, and the unavailability of effective models. With the aim of improving the accuracy of heart sounds classification, an in-depth systematic review and an analysis of existing deep learning methods were performed in the present study, with an emphasis on the convolutional neural network (CNN) and recurrent neural network (RNN) methods developed over the last five years. This paper also discusses the challenges and expected future trends in the application of deep learning to heart sounds classification with the objective of providing an essential reference for further study.