Social Media-Based Surveillance Systems for Health Informatics Using Machine and Deep Learning Techniques:A Comprehensive Review and Open Challenges

Social media(SM)based surveillance systems,combined with machine learning(ML)and deep learning(DL)techniques,have shown potential for early detection of epidemic outbreaks.This review discusses the current state of SM-based surveillance methods for early epidemic outbreaks and the role of ML and DL in enhancing their performance.Since,every year,a large amount of data related to epidemic outbreaks,particularly Twitter data is generated by SM.This paper outlines the theme of SM analysis for tracking health-related issues and detecting epidemic outbreaks in SM,along with the ML and DL techniques that have been configured for the detection of epidemic outbreaks.DL has emerged as a promising ML technique that adaptsmultiple layers of representations or features of the data and yields state-of-the-art extrapolation results.In recent years,along with the success of ML and DL in many other application domains,both ML and DL are also popularly used in SM analysis.This paper aims to provide an overview of epidemic outbreaks in SM and then outlines a comprehensive analysis of ML and DL approaches and their existing applications in SM analysis.Finally,this review serves the purpose of offering suggestions,ideas,and proposals,along with highlighting the ongoing challenges in the field of early outbreak detection that still need to be addressed.

Managing Health Treatment by Optimizing Complex Lab-Developed Test Configurations: A Health Informatics Perspective

A complex Laboratory Developed Test(LDT)is a clinical test developed within a single laboratory.It is typically configured from many fea-ture constraints from clinical repositories,which are part of the existing Lab-oratory Information Management System(LIMS).Although these clinical repositories are automated,support for managing patient information with test results of an LDT is also integrated within the existing LIMS.Still,the support to configure LDTs design needs to be made available even in standard LIMS packages.The manual configuration of LDTs is a complex process and can generate configuration inconsistencies because many constraints between features can remain unsatisfied.It is a risky process and can lead patients to undergo unnecessary treatments.We proposed an optimized solution(opt-LDT)based on Genetic Algorithms to automate the configuration and resolve the inconsistencies in LDTs.Opt-LDT encodes LDT configuration as an optimization problem and generates a consistent configuration that satisfies the constraints of the features.We tested and validated opt-LDT for a local secondary care hospital in a real healthcare environment.Our results,averaged over ten runs,show that opt-LDT resolves 90%of inconsistencies while taking between 6 and 6.5 s for each configuration.Moreover,positive feedback based on a subjective questionnaire from clinicians regarding the performance,acceptability,and efficiency of opt-LDT motivates us to present our results for regulatory approval.

Characteristics and Enlightenment of Health Informatics Education in American Universities

The demand for health information is increasing in China,and China has gradually paid attention to health informatics education.The successful experience of American health informatics education can effectively promote the development of health informatics education in China.This paper analyzes the main characteristics of health informatics education in American colleges and universities by literature survey and network survey,and concludes that Chinese colleges and universities should strengthen practical education,enhance teachers’strength,increase the form of educational projects,and perfect the curriculum content system.

Enriching online access to health information for the public: Efforts from a medical library in China

Purpose: Disseminating medical and health information is a mission of a public medical library. This paper describes a practice of a medical library in providing online access to health information for the general public.Design/methodology/approach: A four-step workflow is developed to integrate and disseminate heterogeneous health information from medical associations. First, a raw data repository is developed to manage the original submissions from information providers.Second, each document in the raw data repository is represented in a standardized XML schema. Third, the medical terms are identified and manually annotated, enriching the semantics of health information. Lastly, all the semantically enriched XML documents are converted to HTMLs for online dissemination.Findings: A health information website, CHealth, was developed for Chinese speakers. It provides free online access for all without any login or IP constrains. CHealth is available at www.chealth.org.cn.Research limitations: The current workflow is time-consuming and labor-intensive due to the lack of information submission/exchange standard and commonly agreed-on consumer health terminology in Chinese.Originality/value: In this work, the target audience of the medical library has been extended from traditional academic/professional to the general public. Methodologies in library sciences have been combined with those in consumer health informatics in CHealth development.

On Monetizing Personal Wearable Devices Data:A Blockchain-based Marketplace for Data Crowdsourcing and Federated Machine Learning in Healthcare

Machine learning advancements in healthcare have made data collected through smartphones and wearable devices a vital source of public health and medical insights.While wearable device data help to monitor,detect,and predict diseases and health conditions,some data owners hesitate to share such sensitive data with companies or researchers due to privacy concerns.Moreover,wearable devices have been recently available as commercial products;thus large,diverse,and representative datasets are not available to most researchers.In this article,the authors propose an open marketplace where wearable device users securely monetize their wearable device records by sharing data with consumers(e.g.,researchers)to make wearable device data more available to healthcare researchers.To secure the data transactions in a privacy-preserving manner,the authors use a decentralized approach using Blockchain and Non-Fungible Tokens(NFTs).To ensure data originality and integrity with secure validation,the marketplace uses Trusted Execution Environments(TEE)in wearable devices to verify the correctness of health data.The marketplace also allows researchers to train models using Federated Learning with a TEE-backed secure aggregation of data users may not be willing to share.To ensure user participation,we model incentive mechanisms for the Federated Learning-based and anonymized data-sharing approaches using NFTs.The authors also propose using payment channels and batching to reduce smart contact gas fees and optimize user profits.If widely adopted,it’s believed that TEE and Blockchain-based incentives will promote the ethical use of machine learning with validated wearable device data in healthcare and improve user participation due to incentives.

Drug-Treatment Generation Combinatorial Algorithm Based on Machine Learning and Statistical Methodologies

Finding out the desired drug combinations is a challenging task because of the number of different combinations that exist and the adversarial effects that may arise. In this work, we generate drug combinations over multiple stages using distance calculation metrics from supervised learning, clustering, and a statistical similarity calculation metric for deriving the optimal treatment sequences. The combination generation happens for each patient based on the characteristics (features) observed during each stage of treatment. Our approach considers not the drug-to-drug (one-to-one) effect, but rather the effect of group of drugs with another group of drugs. We evaluate the combinations using an FNN model and identify future improvement directions.

The Impact of Information Technology on Admission Decisions

Information systems have been adopted in many fields including the health industry. Indeed, keeping abreast of the advances of the technological age, many medical organizations have invested heavily in information technologies （IT）, aiming at improving medical decision-making and increasing its efficiency. Despite their obvious advantages, the systems do not always immediately provide the vital medical information required for critical decision-making, and the decisions that are based on this partial information may result in a decreased level of quality of care and unnecessary costs. The objective of this research is to evaluate the contribution of IT to decision-makers （physicians） at the point of care of emergency departments （EDs） by investigating whether the information systems （IS） have improved the medical outcomes, in the complex and highly stressful environment of the ED, with time constraints and overcrowding. The authors evaluated the contribution of the medical information to admission decisions by using the track log-file analysis method. The results were obtained using a unique database containing referrals to the ED from seven main hospitals in Israel. The authors＇ results lead to the major conclusion that viewing medical history contributes to admission decisions and clearly reduces the number of avoidable admissions.

Men with prostate cancer and the accessibility to information—a literature review

Objective: To explore possible consequences of short stays in hospitals, as these short contacts reduce the patients’ time for information and support. Method: A literature survey was carried out to get an insight in possible consequences by summarizing the state of knowledge on how men with prostate cancer undergoing prostatec-tomy surgery experience their contacts with the healthcare professionals. Results: A consequence is that often men with prostate cancer, treated with prostatectomy surgery, do not receive the individualized support, infor-mation, and dialogue they need, which leads to feelings of uncertainty, insecurity, and loss of control. The men use the Internet in their search for information and support, which makes them able to stay in control and be active, responsible partners in their own course of treatment. Conclusion: For men to feel secure and certain the accessibility of the healthcare professionals and the healthcare professionals’ ability to individualize information and support are important aspects. Practice Implications: It is relevant to provide male cancer patients with tools that can underpin their contact to the healthcare professionals. Utilizing Web 2.0 technologies, Internet based tools can support exchange-ability, towards dialogue-based contacts, between men with prostate cancer and healthcare professionals.

Data Analysis of Multiplex Sequencing at SOLiD Platform:A Probabilistic Approach to Characterization and Reliability Increase

New sequencing technologies such as Illumina/Solexa, SOLiD/ABI, and 454/Roche, revolutionized the biological researches. In this context, the SOLiD platform has a particular sequencing type, known as multiplex run, which enables the sequencing of several samples in a single run. It implies in cost reduction and simplifies the analysis of related samples. Meanwhile, this sequencing type requires an additional filtering step to ensure the reliability of the results. Thus, we propose in this paper a probabilistic model which considers the intrinsic characteristics of each sequencing to characterize multiplex runs and filter low-quality data, increasing the data analysis reliability of multiplex sequencing performed on SOLiD. The results show that the proposed model proves to be satisfactory due to: 1) identification of faults in the sequencing process;2) adaptation and development of new protocols for sample preparation;3) the assignment of a degree of confidence to the data generated;and 4) guiding a filtering process, without discarding useful sequences in an arbitrary manner.

Adversarial attacks and defenses in physiological computing:a systematic review

Physiological computing uses human physiological data as system inputs in real time.It includes,or significantly overlaps with,brain-computer interfaces,affective computing,adaptive automation,health informatics,and physiological signal based biometrics.Physiological computing increases the communication bandwidth from the user to the computer,but is also subject to various types of adversarial attacks,in which the attacker deliberately manipulates the training and/or test examples to hijack the machine learning algorithm output,leading to possible user confusion,frustration,injury,or even death.However,the vulnerability of physiological computing systems has not been paid enough attention to,and there does not exist a comprehensive review on adversarial attacks to them.This study fills this gap,by providing a systematic review on the main research areas of physiological computing,different types of adversarial attacks and their applications to physiological computing,and the corresponding defense strategies.We hope this review will attract more research interests on the vulnerability of physiological computing systems,and more importantly,defense strategies to make them more secure.

Functional Neuroimaging in the New Era of Big Data

The field of functional neuroimaging has substantially advanced as a big data science in the past decade,thanks to international collaborative projects and community efforts.Here we conducted a literature review on functional neuroimaging,with focus on three general challenges in big data tasks:data collection and sharing,data infrastructure construction,and data analysis methods.The review covers a wide range of literature types including perspectives,database descriptions,methodology developments,and technical details.We show how each of the challenges was proposed and addressed,and how these solutions formed the three core foundations for the functional neuroimaging as a big data science and helped to build the current data-rich and data-driven community.Furthermore,based on our review of recent literature on the upcoming challenges and opportunities toward future scientific discoveries,we envisioned that the functional neuroimaging community needs to advance from the current foundations to better data integration infrastructure,methodology development toward improved learning capability,and multi-discipline translational research framework for this new era of big data.