A medical big data access control model based on smart contracts and risk in the blockchain environment.

The rapid development of the Hospital Information System has significantly enhanced the convenience of medical research and the management of medical information. However, the internal misuse and privacy leakage of medical big data are critical issues that need to be addressed in the process of medical research and information management. Access control serves as a method to prevent data misuse and privacy leakage. Nevertheless, traditional access control methods, limited by their single usage scenario and susceptibility to single point failures, fail to adapt to the polymorphic, real-time, and sensitive characteristics of medical big data scenarios. This paper proposes a smart contracts and risk-based access control model (SCR-BAC). This model integrates smart contracts with traditional risk-based access control and deploys risk-based access control policies in the form of smart contracts into the blockchain, thereby ensuring the protection of medical data. The model categorizes risk into historical and current risk, quantifies the historical risk based on the time decay factor and the doctor's historical behavior, and updates the doctor's composite risk value in real time. The access control policy, based on the comprehensive risk, is deployed into the blockchain in the form of a smart contract. The distributed nature of the blockchain is utilized to automatically enforce access control, thereby resolving the issue of single point failures. Simulation experiments demonstrate that the access control model proposed in this paper effectively curbs the access behavior of malicious doctors to a certain extent and imposes a limiting effect on the internal abuse and privacy leakage of medical big data.

Domain adaptive learning for multi realm sentiment classification on big data.

Machine learning techniques that rely on textual features or sentiment lexicons can lead to erroneous sentiment analysis. These techniques are especially vulnerable to domain-related difficulties, especially when dealing in Big data. In addition, labeling is time-consuming and supervised machine learning algorithms often lack labeled data. Transfer learning can help save time and obtain high performance with fewer datasets in this field. To cope this, we used a transfer learning-based Multi-Domain Sentiment Classification (MDSC) technique. We are able to identify the sentiment polarity of text in a target domain that is unlabeled by looking at reviews in a labelled source domain. This research aims to evaluate the impact of domain adaptation and measure the extent to which transfer learning enhances sentiment analysis outcomes. We employed transfer learning models BERT, RoBERTa, ELECTRA, and ULMFiT to improve the performance in sentiment analysis. We analyzed sentiment through various transformer models and compared the performance of LSTM and CNN. The experiments are carried on five publicly available sentiment analysis datasets, namely Hotel Reviews (HR), Movie Reviews (MR), Sentiment140 Tweets (ST), Citation Sentiment Corpus (CSC), and Bioinformatics Citation Corpus (BCC), to adapt multi-target domains. The performance of numerous models employing transfer learning from diverse datasets demonstrating how various factors influence the outputs.

Big data empowerment: Digital transformation and governance of minority shareholders: Evidence from China.

Based on the analysis of data from listed enterprises in China between 2011 and 2022, we investigate the influence of digital transformation on the governance efficiency for minority shareholders. The results show that the extent of digital transformation exert a negative effect on the agency costs incurred from related-party transactions. The mechanism examination elucidates that digital transformation augments the governance efficiency for minority shareholders by boosting attendance at shareholders' meetings and enhancing the exit threat for minority shareholders. Subsequent analysis reveals that non-state-owned enterprises, compared to state-owned enterprises, exhibit a more pronounced effect in diminishing the second type of agency costs through digital transformation. Furthermore, the impact of digital transformation in curtailing agency costs is more significant in the eastern regions than central and western regions. The better the equity checks and balances in listed enterprises, the more effective digital transformation is in reducing agency costs. This study offers valuable insights for bolstering the governance capacity of minority shareholders in the context of digital transformation.

Influencing factors and countermeasures on intelligent transformation and upgrading of logistics firms: A case study in China.

This study explores the influencing factors on intelligent transformation and upgrading of China's logistics firms under smart logistics, and designs the corresponding framework to guide the practice of firms. By analyzing the characteristics of smart logistics and the transformation and upgrading needs of traditional logistics, from the micro perspective of logistics firms, this paper constructs influencing factor index system of smart transformation and development from four dimensions: logistics technology innovation, logistics big data sharing, logistics management upgrading and logistics decision-making transformation. Logistics firms are divided into firms with medium scale and above and small and medium-sized firms according to their scale. Then EWIF-AHP model is proposed to measure the weight of index system and score the decision-making, so as to evaluate the impact of various influencing factors on transformation and development of logistics firms. The results show that, for logistics firms above medium scale, logistics technology innovation and logistics big data sharing have the most significant impact on transformation and development, followed by logistics management upgrading and logistics decision-making transformation. For small and medium-sized logistics firms, the biggest factor is the upgrading of logistics management, followed by the upgrading of logistics technology, which is almost as important as the influencing factors of the upgrading of logistics management, and followed by the sharing of logistics big data and the transformation of logistics decision-making. Therefore, corresponding countermeasures and suggestions for intelligent transformation of logistics firms have been put forward.

Hybrid disease prediction approach leveraging digital twin and metaverse technologies for health consumer.

Emerging from the convergence of digital twin technology and the metaverse, consumer health (MCH) is witnessing a transformative shift. The amalgamation of bioinformatics with healthcare Big Data has ushered in a new era of disease prediction models that harness comprehensive medical data, enabling the anticipation of illnesses even before the onset of symptoms. In this model, deep neural networks stand out because they improve accuracy remarkably by increasing network depth and making weight changes using gradient descent. Nonetheless, traditional methods face their own set of challenges, including the issues of gradient instability and slow training. In this case, the Broad Learning System (BLS) stands out as a good alternative. It gets around the problems with gradient descent and lets you quickly rebuild a model through incremental learning. One problem with BLS is that it has trouble extracting complex features from complex medical data. This makes it less useful in a wide range of healthcare situations. In response to these challenges, we introduce DAE-BLS, a novel hybrid model that marries Denoising AutoEncoder (DAE) noise reduction with the efficiency of BLS. This hybrid approach excels in robust feature extraction, particularly within the intricate and multifaceted world of medical data. Validation using diverse datasets yields impressive results, with accuracies reaching as high as 98.50%. DAE-BLS's ability to rapidly adapt through incremental learning holds great promise for accurate and agile disease prediction, especially within the complex and dynamic healthcare scenarios of today.

Deus Ex Machina? The Rise of Artificial Intelligence in Toxicology.

Artificial intelligence (AI) is rising rapidly, driven by big data, complex algorithms, and computing resources. Current research presented at the American Chemical Society Fall 2023 Meeting demonstrates AI to be a valuable predictive and supporting tool across all facets of toxicology.

Harnessing Big Data in Critical Care: Exploring a new European Dataset.

Freely available datasets have become an invaluable tool to propel data-driven research, especially in the field of critical care medicine. However, the number of datasets available is limited. This leads to the repeated reuse of datasets, inherently increasing the risk of selection bias. Additionally, the need arose to validate insights derived from one dataset with another. In 2023, the Salzburg Intensive Care database (SICdb) was introduced. SICdb offers insights in currently 27,386 intensive care admissions from 21,583 patients. It contains cases of general and surgical intensive care from all disciplines. Amongst others SICdb contains information about: diagnosis, therapies (including data on preceding surgeries), scoring, laboratory values, respiratory and vital signals, and configuration data. Data for SICdb (1.0.6) was collected at one single tertiary care institution of the Department of Anesthesiology and Intensive Care Medicine at the Salzburger Landesklinik (SALK) and Paracelsus Medical University (PMU) between 2013 and 2021. This article aims to elucidate on the characteristics of the dataset, the technical implementation, and provides analysis of its strengths and limitations.

Preparation and Challenges in Developing a Big Data Analysis Framework in Occupational Medicine in Indonesia.

This mini review explores the transformative potential of big data analysis and artificial intelligence (AI) in reforming occupational medicine in Indonesia. Emphasizing the preconditions, case studies, and benefits, it underscores the role of big data in enhancing worker well-being. The review highlights the importance of informative health big data, especially in high-risk industries, with examples of case studies of AI implementation in occupational medicine during the COVID-19 pandemic and other relevant scenarios. While acknowledging the challenges of AI implementation, the essay identifies the role of academic and professional organizations as pioneers in big data utilization. Six potential benefits that are identified, including improved patient care and efficient resource allocation, demonstrate the transformative impact of big data analysis. The proposed pathway of preparation underscores the need for awareness, skill enhancement, and collaboration, addressing challenges in data management and stakeholder engagement. The conclusion emphasizes continuous assessment, feasibility studies, and commitment as essential steps in advancing occupational medicine through big data analysis.

Effect of Esketamine on perioperative anxiety and depression in women with systemic tumors based on big data medical background.

OBJECTIVE: Perioperative anxiety and depression syndrome (PADS) is a common clinical concern among women with systemic tumors. Esketamine has been considered for its potential to alleviate anxiety and depressive symptoms. However, its specific application and effectiveness in PADS among women with systemic tumors remain unclear. This study aimed to analyze the utility of Machine Learning (ML) algorithms based on electroencephalogram (EEG) signals in evaluating perioperative anxiety and depression in women with systemic tumors treated with Esketamine, utilizing a large-scale medical data background. PATIENTS AND METHODS: A single-center, randomized, placebo-controlled (SC-RPC) trial design was adopted. A total of 112 female patients with systemic tumors and PADS who received Esketamine treatment were included as study participants. A moderate dose (0.7 mg/kg) of Esketamine was administered through intravenous infusion over a duration of 60 minutes. EEG signals were collected from all patients, and the EEG signal features of individuals with depression were compared to those without depression. In this study, a Support Vector Machine (SVM)-K-Nearest Neighbour (KNN) hybrid classifier was constructed based on SVM and KNN algorithms. Using the EEG signals, the classifier was utilized to assess the anxiety and depression status of the patients. The predictive performance of the classifier was evaluated using accuracy, sensitivity, and specificity measures. RESULTS: The C2 correntropy feature of the delta rhythm in the left-brain EEG signal was significantly higher in individuals with depression compared to those without depression (p<0.05). Moreover, the C2 correntropy feature of the Alpha, Beta, and Gamma rhythms in the left-brain EEG signal was significantly lower in individuals with depression compared to those without depression (p<0.05). In the right brain EEG signal, the C2 correntropy feature of the delta rhythm was significantly higher in individuals with depression (p<0.05), while the C2 correntropy feature of the alpha and gamma rhythms was significantly lower in individuals with depression compared to those without depression (p<0.05). Additionally, the C1 correntropy feature of the Gamma rhythm in the right brain EEG signal was significantly higher in individuals with depression compared to those without depression (p<0.05). The SVM classifier achieved accuracy, sensitivity, and specificity of 98.23%, 98.10%, and 98.56%, respectively, in recognizing the left-brain EEG signals, with a correlation coefficient of 0.95. In recognizing the right brain EEG signals, the SVM classifier achieved accuracy, sensitivity, and specificity of 98.74%, 98.43%, and 99.03%, respectively, with a correlation coefficient of 0.96. The improved SVM-KNN approach yielded an accuracy, recall, precision, F-score, area over the curve (AOC), and Receiver Operation Characteristics (ROC) of 0.829, 0.811, 0.791, 0.853, 0.787, and 0.877, respectively, in predicting anxiety. For predicting depression, the accuracy, recall, precision, F-score, AOC, and ROC were 0.869, 0.842, 0.831, 0.893, 0.827, and 0.917, respectively. CONCLUSIONS: Significant differences were observed in the brain EEG signals between individuals with depression and those without depression. The improved SVM-KNN algorithm developed in this study demonstrates good predictive capability for anxiety and depression.

Using big data to analyze the vaccination status of children with congenital heart disease in Yinzhou District, China.

Congenital heart disease (CHD) represents a significant population warranting particular attention concerning vaccination coverage. To comprehend the vaccination status of CHD within Yinzhou District, Ningbo City, China, and to facilitate the formulation of preventive, control, and immunization strategies against vaccine-preventable diseases in children with congenital heart conditions. Using the China Yinzhou Electronic Health Record Study (CHERRY) database, we analyzed the vaccination coverage of children with CHD born between January 1, 2016 and September 20, 2021, and analyzed the influencing factors associated with the level of vaccination coverage. This study involved 762 children diagnosed with CHD at the age of 12 months, revealing that 86.74% of these children had received at least one dose of the National Immunization Program (NIP) vaccines. The coverage for non-NIP vaccines, such as the rotavirus vaccine, influenza vaccine, Influenza Haemophilus influenzae Type b (Hib) Conjugate Vaccine, 13-valent pneumococcal conjugate vaccine (PCV13), and inactivated enterovirus type 71 vaccine (EV71), stood at 27.30%, 7.74%, 63.25%, 33.76%, and 34.51%, respectively. The completion coverage for the entire vaccination schedule were 27.30%, 5.51%, 55.77%, 34.25%, and 25.59%, respectively. There was a statistically significant correlation between vaccination coverage in classification of diagnostic medical institutions and the types of diagnosed diseases. Compared to their typically developing counterparts, 12-month-old children afflicted with CHD exhibit a slightly diminished vaccination coverage, alongside a discernible inclination toward delayed vaccination. Notably, the determination to undergo vaccinations seems predominantly influenced by the classification of diagnostic medical institutions. In practical terms, proactive measures involving early diagnosis, comprehensive health assessments, and timely interventions ought to be implemented to enhance vaccination rates while prioritizing safety.

Examining the relationship between COVID-19 and suicide in media coverage through Natural Language Processing analysis

Background and objectives Suicide is a major public health concern, media can influence its awareness, contagion, and prevention. In this study, we evaluated the relationship between the COVID-19 pandemic and suicide in media coverage through Natural Language Processing analysis (NPL). Methods To study how suicide is depicted in news media, Artificial Intelligence and Big Data techniques were used to analyze news and tweets, to extract or classify the topic to which they belonged. Results A granger causality analysis showed with significant p-value that an increase in covid news at the beginning of the pandemic explains a later rise in suicide-related news. An analysis based on correlation and structural causal models show a strong relationship between the appearance of subjects “health” and “covid”, and also between “covid” and “suicide”. Conclusions Our analysis also uncovers that the inclusion of suicide-related news in the category health has grown since the outbreak of the pandemic. The COVID-19 pandemic has posed an inflection point in the way suicide-related news are reported. Our study found that the increased media attention on suicide during the COVID-19 pandemic may indicate rising social awareness of suicide and mental health, which could lead to the development of new prevention tools. (AU)

Anesthesia decision analysis using a cloud-based big data platform.

Big data technologies have proliferated since the dawn of the cloud-computing era. Traditional data storage, extraction, transformation, and analysis technologies have thus become unsuitable for the large volume, diversity, high processing speed, and low value density of big data in medical strategies, which require the development of novel big data application technologies. In this regard, we investigated the most recent big data platform breakthroughs in anesthesiology and designed an anesthesia decision model based on a cloud system for storing and analyzing massive amounts of data from anesthetic records. The presented Anesthesia Decision Analysis Platform performs distributed computing on medical records via several programming tools, and provides services such as keyword search, data filtering, and basic statistics to reduce inaccurate and subjective judgments by decision-makers. Importantly, it can potentially to improve anesthetic strategy and create individualized anesthesia decisions, lowering the likelihood of perioperative complications.

[Patients torn to pieces.] / Pazienti fatti a pezzi.

Dissecting bodies is a common practice in many cultures. But in "big data medicine", the art of dissecting the human body has become an obsession. Indeed, modern biotechnology allows us to see and measure the molecular components of every single cell. But how can we put this immense number of bits and pieces back together again and see the patient as a whole? The first turning point is that proposed by René Descartes, who, inspired by dreams and visions, conceived the idea of unifying all scientific disciplines through the pervasive application of mathematics. Descartes formulates four basic rules, the second (top-down method) and third (bottom-up method) of which become crucial in modern data analysis. An instructive case study considered here is that of pulmonary tuberculosis, where the Cartesian approach of decomposing problems into smaller and smaller "pieces" - from organism to organ and from cellular lesion to the microscopic level - has led to the cure of the disease through antibiotics. This success story inspired Paul Ehrlich who, with the concept of the "magic bullet", defined modern pharmacology. However, this paradigm is being challenged today by multifactorial diseases and big data medicine, where the enormous availability of clinical and molecular data must be integrated to arrive at a therapeutic decision. The Cartesian approach shows its limitations today, as witnessed by the similar difficulty in fields other than medicine, illustrated here by the case of choosing to produce a successful television series based on user profiling. The take-home message is that the amount of data collected does not automatically guarantee success but that, instead of being data-driven, a collective "human" overview and assessment is inevitable. That is, close collaboration between clinicians and data analysts, integrating expertise, is needed to address challenges in the diagnosis and treatment of complex diseases through imagination and not mere extrapolation.

Harnessing Big Data in Amyotrophic Lateral Sclerosis: Machine Learning Applications for Clinical Practice and Pharmaceutical Trials.

The arrival of genotype-specific therapies in amyotrophic lateral sclerosis (ALS) signals the dawn of precision medicine in motor neuron diseases (MNDs). After decades of academic studies in ALS, we are now witnessing tangible clinical advances. An ever increasing number of well-designed descriptive studies have been published in recent years, characterizing typical disease-burden patterns in vivo and post mortem. Phenotype- and genotype-associated traits and "typical" propagation patterns have been described based on longitudinal clinical and biomarker data. The practical caveat of these studies is that they report "group-level", stereotyped trajectories representative of ALS as a whole. In the clinical setting, however, "group-level" biomarker signatures have limited practical relevance and what matters is the meaningful interpretation of data from a single individual. The increasing availability of large normative data sets, national registries, extant academic data, consortium repositories, and emerging data platforms now permit the meaningful interpretation of individual biomarker profiles and allow the categorization of single patients into relevant diagnostic, phenotypic, and prognostic categories. A variety of machine learning (ML) strategies have been recently explored in MND to demonstrate the feasibility of interpreting data from a single patient. Despite the considerable clinical prospects of classification models, a number of pragmatic challenges need to be overcome to unleash the full potential of ML in ALS. Cohort size limitations, administrative hurdles, data harmonization challenges, regulatory differences, methodological obstacles, and financial implications and are just some of the barriers to readily implement ML in routine clinical practice. Despite these challenges, machine-learning strategies are likely to be firmly integrated in clinical decision-making and pharmacological trials in the near future.

Graph Neural Network contextual embedding for Deep Learning on tabular data.

All industries are trying to leverage Artificial Intelligence (AI) based on their existing big data which is available in so called tabular form, where each record is composed of a number of heterogeneous continuous and categorical columns also known as features. Deep Learning (DL) has constituted a major breakthrough for AI in fields related to human skills like natural language processing, but its applicability to tabular data has been more challenging. More classical Machine Learning (ML) models like tree-based ensemble ones usually perform better. This paper presents a novel DL model using Graph Neural Network (GNN) more specifically Interaction Network (IN), for contextual embedding and modeling interactions among tabular features. Its results outperform those of a recently published survey with DL benchmark based on seven public datasets, also achieving competitive results when compared to boosted-tree solutions.