Optimizing Healthcare Big Data Processing with Containerized PySpark and Parallel Computing: A Study on ETL Pipeline Efficiency

In this study, we delve into the realm of efficient Big Data Engineering and Extract, Transform, Load (ETL) processes within the healthcare sector, leveraging the robust foundation provided by the MIMIC-III Clinical Database. Our investigation entails a comprehensive exploration of various methodologies aimed at enhancing the efficiency of ETL processes, with a primary emphasis on optimizing time and resource utilization. Through meticulous experimentation utilizing a representative dataset, we shed light on the advantages associated with the incorporation of PySpark and Docker containerized applications. Our research illuminates significant advancements in time efficiency, process streamlining, and resource optimization attained through the utilization of PySpark for distributed computing within Big Data Engineering workflows. Additionally, we underscore the strategic integration of Docker containers, delineating their pivotal role in augmenting scalability and reproducibility within the ETL pipeline. This paper encapsulates the pivotal insights gleaned from our experimental journey, accentuating the practical implications and benefits entailed in the adoption of PySpark and Docker. By streamlining Big Data Engineering and ETL processes in the context of clinical big data, our study contributes to the ongoing discourse on optimizing data processing efficiency in healthcare applications. The source code is available on request.

Big Data Analytics in Healthcare——A Systematic Literature Review and Roadmap for Practical Implementation

The advent of healthcare information management systems(HIMSs)continues to produce large volumes of healthcare data for patient care and compliance and regulatory requirements at a global scale.Analysis of this big data allows for boundless potential outcomes for discovering knowledge.Big data analytics(BDA)in healthcare can,for instance,help determine causes of diseases,generate effective diagnoses,enhance Qo S guarantees by increasing efficiency of the healthcare delivery and effectiveness and viability of treatments,generate accurate predictions of readmissions,enhance clinical care,and pinpoint opportunities for cost savings.However,BDA implementations in any domain are generally complicated and resource-intensive with a high failure rate and no roadmap or success strategies to guide the practitioners.In this paper,we present a comprehensive roadmap to derive insights from BDA in the healthcare(patient care)domain,based on the results of a systematic literature review.We initially determine big data characteristics for healthcare and then review BDA applications to healthcare in academic research focusing particularly on No SQL databases.We also identify the limitations and challenges of these applications and justify the potential of No SQL databases to address these challenges and further enhance BDA healthcare research.We then propose and describe a state-of-the-art BDA architecture called Med-BDA for healthcare domain which solves all current BDA challenges and is based on the latest zeta big data paradigm.We also present success strategies to ensure the working of Med-BDA along with outlining the major benefits of BDA applications to healthcare.Finally,we compare our work with other related literature reviews across twelve hallmark features to justify the novelty and importance of our work.The aforementioned contributions of our work are collectively unique and clearly present a roadmap for clinical administrators,practitioners and professionals to successfully implement BDA initiatives in their organizations.

Standard NER Tagging Scheme for Big Data Healthcare Analytics built on Unified Medical Corpora

The motivation for this research comes from the gap found in discovering the common ground for medical context learning through analytics for different purposes of diagnosing,recommending,prescribing,or treating patients for uniform phenotype features from patients’profile.The authors of this paper while searching for possible solutions for medical context learning found that unified corpora tagged with medical nomenclature was missing to train the analytics for medical context learning.Therefore,here we demonstrated a mechanism to come up with uniform NER(Named Entity Recognition)tagged medical corpora that is fed with 14407 endocrine patients’data set in Comma Separated Values(CSV)format diagnosed with diabetes mellitus and comorbidity diseases.The other corpus is of ICD-10-CM coding scheme in text format taken from www.icd10data.com.ICD-10-CM corpus is to be tagged for understanding the medical context with uniformity for which we are conducting different experiments using common natural language programming(NLP)techniques and frameworks like TensorFlow,Keras,Long Short-Term Memory(LSTM),and Bi-LSTM.In our preliminary experiments,albeit label sets in form of(instance,label)pair were tagged with Sequential()model formed on TensorFlow.Keras and Bi-LSTM NLP algorithms.The maximum accuracy achieved for model validation was 0.8846.

Big data in healthcare:Conceptual network structure,key challenges and opportunities

Big data is a concept that deals with large or complex data sets by using data analysis tools(e.g.,data mining,machine learning)to analyze information extracted from several sources systematically.Big data has attracted wide attention from academia,for example,in supporting patients and health professionals by improving the accuracy of decision-making,diagnosis and disease prediction.This research aimed to perform a Bibliometric Performance and Network Analysis(BPNA)supported by a Scoping Review(SR)to depict the strategic themes,thematic evolution structure,main challenges and opportunities related to the concept of big data applied in the healthcare sector.With this goal in mind,4857 documents from the Web of Science covering the period between 2009 to June 2020 were analyzed with the support of SciMAT software.The bibliometric performance showed the number of publications and citations over time,scientific productivity and the geographic distribution of publications and research fields.The strategic diagram yielded 20 clusters and their relative importance in terms of centrality and density.The thematic evolution structure presented the most important themes and how it changes over time.Lastly,we presented the main challenges and future opportunities of big data in healthcare.

In the wave of big data,can traditional medicine for the diagnosis and treatment of skeletal disorders be given a new lease of life?

In recent years,big data has become a buzzword in the internet sector,gradually being used in various industries and fields,and has already yielded considerable benefits in e-commerce.In the past few years,big data has become increasingly important in healthcare based on the massive volume of clinical data and the increasing demand for personalized medicine.Traditional medicine,one of humanity’s fabulous creations,has also contributed actively to preventing and controlling new epidemics.With the development of the Internet,AI,cloud computing,the Internet of Things,and other high technologies in recent years,new vitality has been injected into the development of traditional medicine.It has also provided strong support for conventional medicine to play a more excellent value.Traditional medicine is now flourishing and gradually moving into the era of big data.Recently,there has been an increasing number of medical studies related to big data,but more studies are focused on cancer survival and cancer metastasis,which may be related to the fact that there are more free databases related to oncology,similar to the studies on big data related to skeletal diseases,but there are not many studies on the linkage between traditional medicine and big data for skeletal diseases.So,how will the field of big data and traditional medicine combine and diagnose or treat skeletal-related diseases in the future?How can traditional medicine in skeletal disorders ride the current fast-growing big data train?Will big data bring a new lease of life to traditional medicine in skeletal disorders?This review intends to systematically elaborate on the current and future research in the direction of big data in relation to diagnosing and treating skeletal diseases in traditional medicine.

Challenges and opportunities of big data analytics in healthcare

Data science is an interdisciplinary discipline that employs big data,machine learning algorithms,data mining techniques,and scientific methodologies to extract insights and information from massive amounts of structured and unstructured data.The healthcare industry constantly creates large,important databases on patient demographics,treatment plans,results of medical exams,insurance coverage,and more.The data that IoT(Internet of Things)devices collect is of interest to data scientists.Data science can help with the healthcare industry's massive amounts of disparate,structured,and unstructured data by processing,managing,analyzing,and integrating it.To get reliable findings from this data,proper management and analysis are essential.This article provides a comprehen-sive study and discussion of process data analysis as it pertains to healthcare applications.The article discusses the advantages and dis-advantages of using big data analytics(BDA)in the medical industry.The insights offered by BDA,which can also aid in making strategic decisions,can assist the healthcare system.

Optimizing Healthcare Outcomes through Data-Driven Predictive Modeling

This study investigates the transformative potential of big data analytics in healthcare, focusing on its application for forecasting patient outcomes and enhancing clinical decision-making. The primary challenges addressed include data integration, quality, privacy issues, and the interpretability of complex machine-learning models. An extensive literature review evaluates the current state of big data analytics in healthcare, particularly predictive analytics. The research employs machine learning algorithms to develop predictive models aimed at specific patient outcomes, such as disease progression and treatment responses. The models are assessed based on three key metrics: accuracy, interpretability, and clinical relevance. The findings demonstrate that big data analytics can significantly revolutionize healthcare by providing data-driven insights that inform treatment decisions, anticipate complications, and identify high-risk patients. The predictive models developed show promise for enhancing clinical judgment and facilitating personalized treatment approaches. Moreover, the study underscores the importance of addressing data quality, integration, and privacy to ensure the ethical application of predictive analytics in clinical settings. The results contribute to the growing body of research on practical big data applications in healthcare, offering valuable recommendations for balancing patient privacy with the benefits of data-driven insights. Ultimately, this research has implications for policy-making, guiding the implementation of predictive models and fostering innovation aimed at improving healthcare outcomes.

The status quo and future prospects of digital twins for healthcare

Digital twin technology plays a pivotal role in driving the digital transformation of healthcare services.This review provides a comprehensive overview of the applications of digital twins in the healthcare sector.We elucidate the concept and classification of digital twins for healthcare and provide a detailed account of their current applications in clinical diagnosis,treatment,and hospital operational management.Taking the cardiac digital twin as an example,this review showcases the typical use of digital twins in clinical practice and scientific research.Additionally,the challenges faced by digital twin technology in data collection,model construction,ethics,and regulations were analyzed.Finally,the broad prospects of digital twins in promoting precision and personalization in healthcare are envisioned.

Trends in research on osteoarthritis of the knee in conventional medicine:a bibliometric analysis based on big data from 1990-2022

Background:Osteoarthritis of the knee(KOA)is a chronic degenerative disease.KOA is a growing concern due to its high incidence and the pain and other burdens it places on patients.Traditional medicine is a health care model with a long history that includes nature-based treatments,psycho-psychological types of treatments,and more.Traditional medicine is also more effective in diagnosing and treating KOA,and it has never stopped researching KOA.There are no bibliometric studies analyzing articles on the traditional medical diagnosis and management of KOA.This study aimed to comprehensively analyze and analyze the general trends in the study of KOA in traditional medicine from a bibliometric perspective.Methods:All articles reporting on KOA and traditional medicine from 1 January 1990 to 01 November 2022 were obtained from the Web of Science Core.Some software such as CiteSpace,VOS Viewer and Scimago Graphica were used to analyse the publications,which included authors,citations,journals,references,countries where studies were published,institutions and research keywords.The final visualisations were produced using this data.Results:A total of 769 articles were searched.Peijian Tong was identified as the most contributing and published author in the field,and medicine was identified as the most reputable journal in the field of traditional medicine and osteoarthritis of the knee.China is a global leader in the field and a centre of collaboration in the field,with a major concentration of traditional medicine in Asia,which is consistent with the evidence that traditional medicine originated in Asia.According to the data,“osteoarthritis”,“knee osteoarthritis”,“pain”,and“knee”and“hip”were identified as hot keywords for research in this area.Conclusions:The results of this bibliometric study provide a snapshot of the current state of clinical research in the treatment of KOA in traditional medicine and are well placed to envisage future hotspots and possible trends,and may help to provide researchers with more than enough information with a view to guiding the cutting edge of research in this field and the infinite possibilities for the future.

Sleep disturbances and predictors of nondeployability among active-duty army soldiers: an odds ratio analysis of medical healthcare data from fiscal year 2018

Background:The impact of sleep disorders on active-duty soldiers’medical readiness is not currently quantified.Patient data generated at military treatment facilities can be accessed to create research reports and thus can be used to estimate the prevalence of sleep disturbances and the role of sleep on overall health in service members.The current study aimed to quantify sleep-related health issues and their impact on health and nondeployability through the analysis of U.S.military healthcare records from fiscal year 2018(FY2018).Methods:Medical diagnosis information and deployability profiles(e-Profiles)were queried for all active-duty U.S.Army patients with a concurrent sleep disorder diagnosis receiving medical care within FY2018.Nondeployability was predicted from medical reasons for having an e-Profile(categorized as sleep,behavioral health,musculoskeletal,cardiometabolic,injury,or accident)using binomial logistic regression.Sleep e-Profiles were investigated as a moderator between other e-Profile categories and nondeployability.Results:Out of 582,031 soldiers,48.4%(n=281,738)had a sleep-related diagnosis in their healthcare records,9.7%(n=56,247)of soldiers had e-Profiles,and 1.9%(n=10,885)had a sleep e-Profile.Soldiers with sleep e-Profiles were more likely to have had a motor vehicle accident(p OR(prevalence odds ratio)=4.7,95%CI 2.63–8.39,P≤0.001)or work/duty-related injury(p OR=1.6,95%CI 1.32–1.94,P≤0.001).The likelihood of nondeployability was greater in soldiers with a sleep e-Profile and a musculoskeletal e-Profile(p OR=4.25,95%CI 3.75–4.81,P≤0.001)or work/dutyrelated injury(p OR=2.62,95%CI 1.63–4.21,P≤0.001).Conclusion:Nearly half of soldiers had a sleep disorder or sleep-related medical diagnosis in 2018,but their sleep problems are largely not profiled as limitations to medical readiness.Musculoskeletal issues and physical injury predict nondeployability,and nondeployability is more likely to occur in soldiers who have sleep e-Profiles in addition to these issues.Addressing sleep problems may prevent accidents and injuries that could render a soldier nondeployable.

Metaheuristic Clustering Protocol for Healthcare DataCollection in MobileWireless Multimedia Sensor Networks

Nowadays,healthcare applications necessitate maximum volume of medical data to be fed to help the physicians,academicians,pathologists,doctors and other healthcare professionals.Advancements in the domain of Wireless Sensor Networks(WSN)andMultimediaWireless Sensor Networks(MWSN)are tremendous.M-WMSN is an advanced form of conventional Wireless Sensor Networks(WSN)to networks that use multimedia devices.When compared with traditional WSN,the quantity of data transmission in M-WMSN is significantly high due to the presence of multimedia content.Hence,clustering techniques are deployed to achieve low amount of energy utilization.The current research work aims at introducing a new Density Based Clustering(DBC)technique to achieve energy efficiency inWMSN.The DBC technique is mainly employed for data collection in healthcare environment which primarily depends on three input parameters namely remaining energy level,distance,and node centrality.In addition,two static data collector points called Super Cluster Head(SCH)are placed,which collects the data from normal CHs and forwards it to the Base Station(BS)directly.SCH supports multi-hop data transmission that assists in effectively balancing the available energy.Adetailed simulation analysiswas conducted to showcase the superior performance of DBC technique and the results were examined under diverse aspects.The simulation outcomes concluded that the proposed DBC technique improved the network lifetime to a maximum of 16,500 rounds,which is significantly higher compared to existing methods.

Application of AI and IoT in Clinical Medicine:Summary and Challenges

The application of artificial intelligence(AI)technology in the medical field has experienced a long history of development.In turn,some long-standing points and challenges in the medical field have also prompted diverse research teams to continue to explore AI in depth.With the development of advanced technologies such as the Internet of Things(IoT),cloud computing,big data,and 5G mobile networks,AI technology has been more widely adopted in the medical field.In addition,the in-depth integration of AI and IoT technology enables the gradual improvement of medical diagnosis and treatment capabilities so as to provide services to the public in a more effective way.In this work,we examine the technical basis of IoT,cloud computing,big data analysis and machine learning involved in clinical medicine,combined with concepts of specific algorithms such as activity recognition,behavior recognition,anomaly detection,assistant decision-making system,to describe the scenario-based applications of remote diagnosis and treatment collaboration,neonatal intensive care unit,cardiology intensive care unit,emergency first aid,venous thromboembolism,monitoring nursing,image-assisted diagnosis,etc.We also systematically summarize the application of AI and IoT in clinical medicine,analyze the main challenges thereof,and comment on the trends and future developments in this field.

Research on Herb Pairs of Classical Formulae of ZHANG ZhongJing Using Big Data Technology

Objective To analyze various herbal combinations in Treatise on Exogenous Febrile Diseases(Shang Han Lun,《伤寒论》)and Synopsis of Prescriptions of the Golden Chamber(Jin Gui Yao Lve,《金匮要略》),seeking to identify fundamental rules dictating the selection of herbal combinations through probability models and big data technology.Methods A total of 252 formulae were collected from Treatise on Exogenous Febrile Diseases(Shang Han Lun,《伤寒论》)and Synopsis of Prescriptions of the Golden Chamber(Jin Gui Yao Lve,《金匮要略》)by ZHANG Zhong-Jing.Formulae were then preprocessed with all herb names standardized.The concepts of candidate herb pair and candidate herb pair probability were proposed to analyze the rules of combinations in classical formulae based on probability statistics.MapReduce parallel computing framework of distributed big data technology was adopted to analyze large data samples combined with inverted index algorithm.Results The results showed that the core herbs were Glycyrrhizae Radix Rhizoma(Gan Cao,甘草),Cinnamomi Ramulus(Gui Zhi,桂枝),Zingiberis Rhizoma Recens(Sheng Jiang,生姜),Jujubae Fructus(Da Zao,大枣),Paeoniae Radix Alba(Bai Shao,白芍),etc.43 high-frequency pairs co-occurring 10 times or above were extracted,and 35 of these combinations were recognized as traditional herb pairs,such as Cinnamomi Ramulus(Gui Zhi,桂枝)-Glycyrrhizae Radix Rhizoma(Gan Cao,甘草),Zingiberis Rhizoma Recens(Sheng Jiang,生姜)-Jujubae Fructus(Da Zao,大枣),and Cinnamomi Ramulus(Gui Zhi,桂枝)-Ginseng Radix Et Rhizoma(Ren Shen,人参).The other 8 pairs of combinations,such as Paeoniae Radix Alba(Bai Shao,白芍)-Zingiberis Rhizoma Recens(Sheng Jiang,生姜),Paeoniae Radix Alba(Bai Shao,白芍)-Jujubae Fructus(Da Zao,大枣),and Zingiberis Rhizoma Recens(Sheng Jiang,生姜)-Ginseng Radix Et Rhizoma(Ren Shen,人参),were not defined traditionally,but in connection with commonly used herbs.Classical formulae took the core herbs as principles,focusing on tonifying deficiency,strengthening the spleen and the stomach,strengthening the healthy Qi,and eliminating pathogenic factors.The compatibility pattern of properties involved was mainly acrid and sweet,which reflected the compatibility laws of benefiting Qi and tonifying Yang,replenishing Qi and nourishing blood,etc.Conclusions The research of classical formulae provides common understanding of some basic rules that have been adopted to tackle common illnesses/diseases using herbal medicine.The results help to reinforce theoretical understanding and development of traditional Chinese medicine(TCM),and revealing the hidden rules of combination in TCM data.Analyzing wider data samples of various herbal combinations through computation and big data technology can further optimize the use of TCM.

Intelligent Support System for Healthcare Logistics 4.0 Optimization in the Covid Pandemic Context

The covid pandemic points out inconsistencies and points to improve in the organization of healthcare logistics. Indeed, the dangerousness and the propagation process of the virus imply to increase health security (patient and personal health). In this context, healthcare logistics flows require a new and safety organization improving the hospital performance. The purpose of this paper consists in optimizing healthcare logistics flows by solving problems associated to the internal logistics such as reduction of the personal health wasting time and the protection of both patients and personal health. Then, the methodology corresponds to the use of the hospital sustainable digital transformation as a response to healthcare flows and safety problems. Indeed, social, societal and environmental aspects have to be considered in addition to new technologies such as artificial intelligence (AI), Internet of Things (IoTs), Big data and analytics. These parameters could be used in the healthcare for increasing doctor, nurse, caregiver performance during their daily operations, and patient satisfaction. Indeed, this hospital digital transformation requires the use of large data associated to patients and personal health, algorithms, a performance measurement tool (actual and future state) and a general approach for transforming digitally the hospital flows. The paper findings show that the healthcare logistics performance could be improved with a sustainable digital transformation methodology and an intelligent software tool. This paper aims to develop this healthcare logistics 4.0 methodology and to elaborate the intelligent support system. After an introduction presenting the common hospital flows and their main problems, a literature review will be detailed for showing how existing concepts could contribute to the elaboration of a structured methodology. The structure of the intelligent software tool for the healthcare digital transformation and the tool development processes will be presented. An example will be given for illustrating the development of the tool.

Applying Apache Spark on Streaming Big Data for Health Status Prediction

Big data applications in healthcare have provided a variety of solutions to reduce costs,errors,and waste.This work aims to develop a real-time system based on big medical data processing in the cloud for the prediction of health issues.In the proposed scalable system,medical parameters are sent to Apache Spark to extract attributes from data and apply the proposed machine learning algorithm.In this way,healthcare risks can be predicted and sent as alerts and recommendations to users and healthcare providers.The proposed work also aims to provide an effective recommendation system by using streaming medical data,historical data on a user’s profile,and a knowledge database to make themost appropriate real-time recommendations and alerts based on the sensor’s measurements.This proposed scalable system works by tweeting the health status attributes of users.Their cloud profile receives the streaming healthcare data in real time by extracting the health attributes via a machine learning prediction algorithm to predict the users’health status.Subsequently,their status can be sent on demand to healthcare providers.Therefore,machine learning algorithms can be applied to stream health care data from wearables and provide users with insights into their health status.These algorithms can help healthcare providers and individuals focus on health risks and health status changes and consequently improve the quality of life.

E-Healthcare Supported by Big Data

The era of open information in healthcare has arrived. E-healthcare supported by big data supports the move toward greater trans-parency in healthcare by making decades of stored health data searchable and usable. This paper gives an overview the e-health-care architecture. We discuss the four layers of the architecture-data collection, data transport, data storage, and data analysis-as well as the challenges of data security, data privacy, real-time delivery, and open standard interface. We discuss the necessity of establishing an impeccably secure access mechanism and of enacting strong laws to protect patient privacy.

Big Data Analytics with Optimal Deep Learning Model for Medical Image Classification

In recent years,huge volumes of healthcare data are getting generated in various forms.The advancements made in medical imaging are tremendous owing to which biomedical image acquisition has become easier and quicker.Due to such massive generation of big data,the utilization of new methods based on Big Data Analytics(BDA),Machine Learning(ML),and Artificial Intelligence(AI)have become essential.In this aspect,the current research work develops a new Big Data Analytics with Cat Swarm Optimization based deep Learning(BDA-CSODL)technique for medical image classification on Apache Spark environment.The aim of the proposed BDA-CSODL technique is to classify the medical images and diagnose the disease accurately.BDA-CSODL technique involves different stages of operations such as preprocessing,segmentation,fea-ture extraction,and classification.In addition,BDA-CSODL technique also fol-lows multi-level thresholding-based image segmentation approach for the detection of infected regions in medical image.Moreover,a deep convolutional neural network-based Inception v3 method is utilized in this study as feature extractor.Stochastic Gradient Descent(SGD)model is used for parameter tuning process.Furthermore,CSO with Long Short-Term Memory(CSO-LSTM)model is employed as a classification model to determine the appropriate class labels to it.Both SGD and CSO design approaches help in improving the overall image classification performance of the proposed BDA-CSODL technique.A wide range of simulations was conducted on benchmark medical image datasets and the com-prehensive comparative results demonstrate the supremacy of the proposed BDA-CSODL technique under different measures.

Translation in Data Mining to Advance Personalized Medicine for Health Equity

Personalized medicine is the development of “tailored” therapies that reflect traditional medical approaches with the incorporation of the patient’s unique genetic profile and the environmental basis of the disease. These individualized strategies encompass disease prevention and diagnosis, as well as treatment strategies. Today’s healthcare workforce is faced with the availability of massive amounts of patient- and disease-related data. When mined effectively, these data will help produce more efficient and effective diagnoses and treatment, leading to better prognoses for patients at both the individual and population level. Designing preventive and therapeutic interventions for those patients who will benefit most while minimizing side effects and controlling healthcare costs requires bringing diverse data sources together in an analytic paradigm. A resource to clinicians in the development and application of personalized medicine is largely facilitated, perhaps even driven, by the analysis of “big data”. For example, the availability of clinical data warehouses is a significant resource for clinicians in practicing personalized medicine. These “big data” repositories can be queried by clinicians, using specific questions, with data used to gain an understanding of challenges in patient care and treatment. Health informaticians are critical partners to data analytics including the use of technological infrastructures and predictive data mining strategies to access data from multiple sources, assisting clinicians’ interpretation of data and development of personalized, targeted therapy recommendations. In this paper, we look at the concept of personalized medicine, offering perspectives in four important, influencing topics: 1) the availability of “big data” and the role of biomedical informatics in personalized medicine, 2) the need for interdisciplinary teams in the development and evaluation of personalized therapeutic approaches, and 3) the impact of electronic medical record systems and clinical data warehouses on the field of personalized medicine. In closing, we present our fourth perspective, an overview to some of the ethical concerns related to personalized medicine and health equity.

Time to forge ahead:The Internet of Things for healthcare

Situated at the intersection of technology and medicine,the Internet of Things(IoT)holds the promise of addressing some of healthcare's most pressing challenges,from medical error,to chronic drug shortages,to overburdened hospital systems,to dealing with the COVID-19 pandemic.However,despite considerable recent technological advances,the pace of successful implementation of promising IoT healthcare initiatives has been slow.To inspire more productive collaboration,we present here a simple—but surprisingly underrated—problemoriented approach to developing healthcare technologies.To further assist in this effort,we reviewed the various commercial,regulatory,social/cultural,and technological factors in the development of the IoT.We propose that fog computing—a technological paradigm wherein the burden of computing is shifted from a centralized cloud server closer to the data source—offers the greatest promise for building a robust and scalable healthcare IoT ecosystem.To this end,we explore the key enabling technologies that underpin the fog architecture,from the sensing layer all the way up to the cloud.It is our hope that ongoing advances in sensing,communications,cryptography,storage,machine learning,and artificial intelligence will be leveraged in meaningful ways to generate unprecedented medical intelligence and thus drive improvements in the health of many people.

Construction and Update of an Online Ensemble Score Involving Linear Discriminant Analysis and Logistic Regression

The present aim is to update, upon arrival of new learning data, the parameters of a score constructed with an ensemble method involving linear discriminant analysis and logistic regression in an online setting, without the need to store all of the previously obtained data. Poisson bootstrap and stochastic approximation processes were used with online standardized data to avoid numerical explosions, the convergence of which has been established theoretically. This empirical convergence of online ensemble scores to a reference “batch” score was studied on five different datasets from which data streams were simulated, comparing six different processes to construct the online scores. For each score, 50 replications using a total of 10N observations (N being the size of the dataset) were performed to assess the convergence and the stability of the method, computing the mean and standard deviation of a convergence criterion. A complementary study using 100N observations was also performed. All tested processes on all datasets converged after N iterations, except for one process on one dataset. The best processes were averaged processes using online standardized data and a piecewise constant step-size.