Big Data and Analytics in Healthcare

From big data to better patient outcomes

Among medical specialties, laboratory medicine is the largest producer of structured data and must play a crucial role for the efficient and safe implementation of big data and artificial intelligence in healthcare. The area of personalized therapies and precision medicine has now arrived, with huge data sets not only used for experimental and research approaches, but also in the "real world". Analysis of real world data requires development of legal, procedural and technical infrastructure. The integration of all clinical data sets for any given patient is important and necessary in order to develop a patient-centered treatment approach. Data-driven research comes with its own challenges and solutions. The Findability, Accessibility, Interoperability, and Reusability (FAIR) Guiding Principles provide guidelines to make data findable, accessible, interoperable and reusable to the research community. Federated learning, standards and ontologies are useful to improve robustness of artificial intelligence algorithms working on big data and to increase trust in these algorithms. When dealing with big data, the univariate statistical approach changes to multivariate statistical methods significantly shifting the potential of big data. Combining multiple omics gives previously unsuspected information and provides understanding of scientific questions, an approach which is also called the systems biology approach. Big data and artificial intelligence also offer opportunities for laboratories and the In Vitro Diagnostic industry to optimize the productivity of the laboratory, the quality of laboratory results and ultimately patient outcomes, through tools such as predictive maintenance and "moving average" based on the aggregate of patient results.

Community determinants of COPD exacerbations in elderly patients in Lodz province, Poland: a retrospective observational Big Data cohort study

OBJECTIVES

To evaluate the prevalence and identify demographic, economic and environmental local community determinants of chronic obstructive pulmonary disease (COPD) exacerbations in elderly in primary care using Big Data approach.

DESIGN

Retrospective observational case-control study based on Big Data from the National Health Found, Tax Office and National Statistics Center databases in 2016.

SETTING

Primary care clinics in the Lodz province in Poland.

PARTICIPANTS

472 314 patients aged 65 and older in primary care, including 17 240 patients with COPD and 1784 with exacerbations (including deaths).

OUTCOME MEASURES

Exacerbations with demographic, economic and environmental local community determinants were retrieved. Conditional logistic regression for matched pairs was used to evaluate the local community determinants of COPD exacerbations among patients with COPD.

RESULTS

The overall prevalence of COPD in the population of elderly patients registered in primary healthcare clinic clinics in Lodz province in 2016 was 3.65%, 95% CI (3.60% to 3.70%) and the prevalence of exacerbations was 10.35%, 95% CI (9.89% to 10.80%). The high number of consultations in primary care clinics was associated with higher risk of COPD exacerbations (p=0.0687).High-income patients were less likely to have exacerbations than low-income patients (high vs low OR 0.601, 95% CI (0.385 to 0.939)). The specialisation of the primary care physician did not have an effect on exacerbations (OR 1.076, 95% CI (0.920 to 1.257)). Neither the forest cover per gmina (high vs low OR 0.897, 95% CI (0.605 to 1.331); medium vs low OR 0.925, 95% CI (0.648 to 1.322)), nor location of gmina (urban vs urban-rural OR 1.044; 95% CI (0.673 to 1.620)), (rural vs urban-rural OR 0.897, 95% CI (0.630 to 1.277)) appears to influence COPD exacerbations.

CONCLUSIONS

Big Data statistical analysis facilitated the evaluation of the prevalence and determinants of COPD exacerbation in the elderly residents of Lodz province, Poland.Modification of identified local community determinants may potentially decrease the number of exacerbations in elderly patients with COPD.

RBC Inventory-Management System Based on XGBoost Model

It is difficult to predict RBC consumption accurately. This paper aims to use big data to establish a XGBoost Model to understand the trend of RBC accurately, and forecast the demand in time. XGBoost, which implements machine learning algorithms under the Gradient Boosting framework can provide a parallel tree boosting. The daily RBC usage and inventory (May 2014-September 2017) were investigated, and rules for RBC usage were analysed. All data were divided into training sets and testing sets. A XGBoost Model was established to predict the future RBC demand for durations ranging from a day to a week. In addition, the alert range was added to the predicted value to ensure RBC demand of emergency patients and surgical accidents. The gap between RBC usage and inventory was fluctuant, and had no obvious rule. The maximum residual inventory of a certain blood group was up to 700 units one day, while the minimum was nearly 0 units. Upon comparing MAE (mean absolute error):A:10.69, B:11.19, O:10.93, and AB:5.91, respectively, the XGBoost Model was found to have a predictive advantage over other state-of-the-art approaches. It showed the model could fit the trend of daily RBC usage. An alert range could manage the demand of emergency patients or surgical accidents. The model had been built to predict RBC demand, and the alert range of RBC inventory is designed to increase the safety of inventory management.

Connecting and linking neurocognitive, digital phenotyping, physiologic, psychophysical, neuroimaging, genomic, & sensor data with survey data

Combining survey data with alternative data sources (e.g., wearable technology, apps, physiological, ecological monitoring, genomic, neurocognitive assessments, brain imaging, and psychophysical data) to paint a complete biobehavioral picture of trauma patients comes with many complex system challenges and solutions. Starting in emergency departments and incorporating these diverse, broad, and separate data streams presents technical, operational, and logistical challenges but allows for a greater scientific understanding of the long-term effects of trauma. Our manuscript describes incorporating and prospectively linking these multi-dimensional big data elements into a clinical, observational study at US emergency departments with the goal to understand, prevent, and predict adverse posttraumatic neuropsychiatric sequelae (APNS) that affects over 40 million Americans annually. We outline key data-driven system challenges and solutions and investigate eligibility considerations, compliance, and response rate outcomes incorporating these diverse "big data" measures using integrated data-driven cross-discipline system architecture.

Big data simulations for capacity improvement in a general ophthalmology clinic

Purpose

Long total waiting times (TWT) experienced by patients during a clinic visit have a significant adverse effect on patient’s satisfaction. Our aim was to use big data simulations of a patient scheduling calendar and its effect on TWT in a general ophthalmology clinic. Based on the simulation, we implemented changes to the calendar and verified their effect on TWT in clinical practice.

Design and methods

For this retrospective simulation study, we generated a discrete event simulation (DES) model based on clinical timepoints of 4.401 visits to our clinic. All data points were exported from our clinical warehouse for further processing. If not available from the electronic health record, manual time measurements of the process were used. Various patient scheduling models were simulated and evaluated based on their reduction of TWT. The most promising model was implemented into clinical practice in 2017.

Results

During validation of our simulation model, we achieved a high agreement of mean TWT between the real data (229 ± 100 min) and the corresponding simulated data (225 ± 112 min). This indicates a high quality of the simulation model. Following the simulations, a patient scheduling calendar was introduced, which, compared with the old calendar, provided block intervals and extended time windows for patients. The simulated TWT of this model was 153 min. After implementation in clinical practice, TWT per patient in our general ophthalmology clinic has been reduced from 229 ± 100 to 183 ± 89 min.

Conclusion

By implementing a big data simulation model, we have achieved a cost-neutral reduction of the mean TWT by 21%. Big data simulation enables users to evaluate variations to an existing system before implementation into clinical practice. Various models for improving patient flow or reducing capacity loads can be evaluated cost-effectively.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00417-020-05040-9.

Big data and artificial intelligence in future patient management. How is it all started? Where are we at now? Quo tendimus?

Background

This article is focused on the understanding of the key points and their importance and impact on the future of early disease predictive models, accurate and fast diagnosis, patient management, optimise treatment, precision medicine, and allocation of resources through the applications of Big Data (BD) and Artificial Intelligence (AI) in healthcare.

Content

BD and AI processes include learning which is the acquisition of information and rules for using the information, reasoning which is using rules to reach approximate or definite conclusions and self-correction. This can help improve the detection of diseases, rare diseases, toxicity, identifying health system barriers causing under-diagnosis. BD combined with AI, Machine Learning (ML), computing and predictive-modelling, and combinatorics are used to interrogate structured and unstructured data computationally to reveal patterns, trends, potential correlations and relationships between disparate data sources and associations.

Summary

Diagnosis-assisted systems and wearable devices will be part and parcel not only of patient management but also in the prevention and early detection of diseases. Also, Big Data will have an impact on payers, devise makers and pharmaceutical companies. BD and AI, which is the simulation of human intelligence processes, are more diverse and their application in monitoring and diagnosis will only grow bigger, wider and smarter.

Outlook

BD connectivity and AI of diagnosis-assisted systems, wearable devices and smartphones are poised to transform patient and to change the traditional methods for patient management, especially in an era where is an explosion in medical data.

Potentials of Digitalization in Sports Medicine: A Narrative Review

Digital transformation is becoming increasingly common in modern life and sports medicine, like many other medical disciplines, it is strongly influenced and impacted by this rapidly changing field. This review aims to give a brief overview of the potential that digital technologies can have for health care providers and patients in the clinical practice of sports medicine. We will focus on mobile applications, wearables, smart devices, intelligent machines, telemedicine, artificial intelligence, big data, system interoperability, virtual reality, augmented reality, exergaming, or social networks. While some technologies are already used in current medical practice, others still have undiscovered potential. Due to the diversity and ever changing nature of this field, we will briefly review multiple areas in an attempt to give readers some general exposure to the landscape instead of a thorough, deep review of one topic. Further research will be necessary to show how digitalization applications could best be used for patient treatments.

MISS-D: A fast and scalable framework of medical image storage service based on distributed file system

Background and Objective Processing of medical imaging big data is deeply challenging due to the size of data, computational complexity, security storage and inherent privacy issues. Traditional picture archiving and communication system, which is an imaging technology used in the healthcare industry, generally uses centralized high performance disk storage arrays in the practical solutions. The existing storage solutions are not suitable for the diverse range of medical imaging big data that needs to be stored reliably and accessed in a timely manner. The economical solution is emerging as the cloud computing which provides scalability, elasticity, performance and better managing cost. Cloud based storage architecture for medical imaging big data has attracted more and more attention in industry and academia. Methods This study presents a novel, fast and scalable framework of medical image storage service based on distributed file system. Two innovations of the framework are introduced in this paper. An integrated medical imaging content indexing file model for large-scale image sequence is designed to adapt to the high performance storage efficiency on distributed file system. A virtual file pooling technology is proposed, which uses the memory-mapped file method to achieve an efficient data reading process and provides the data swapping strategy in the pool. Result The experiments show that the framework not only has comparable performance of reading and writing files which meets requirements in real-time application domain, but also bings greater convenience for clinical system developers by multiple client accessing types. The framework supports different user client types through the unified micro-service interfaces which basically meet the needs of clinical system development especially for online applications. The experimental results demonstrate the framework can meet the needs of real-time data access as well as traditional picture archiving and communication system. Conclusions This framework aims to allow rapid data accessing for massive medical images, which can be demonstrated by the online web client for MISS-D framework implemented in this paper for real-time data interaction. The framework also provides a substantial subset of features to existing open-source and commercial alternatives, which has a wide range of potential applications.

Moderating Effects of Gender and Resistance to Change on the Adoption of Big Data Analytics in Healthcare

The big data analytics (BDA) has dragged tremendous attention in healthcare organizations. Healthcare organizations are investing substantial money and time in big data analytics and want to adopt it to get potential benefits. Thus, this study proposes a BDA adoption model in healthcare organizations to explore the critical factors that can influence its adoption process. The study extends the technology acceptance model (TAM) with the self-efficacy as an external factor and also includes gender and resistance to change (RTC) as moderators to strengthen the research model. The proposed research model has been tested on 283 valid responses which were collected through a structured survey, by applying structural equation modeling. Our results portray that self-efficacy is a strong predictor of intention to use BDA along with other TAM factors. Moreover, it is confirmed by the results that RTC dampens the positive relationship between intention to use and actual use of BDA in healthcare organizations. The outcomes revealed that male employees as compared to female employees are dominant towards the positive intention to use BDA. Furthermore, females create more RTC than males while adopting BDA in healthcare organizations. Theoretical and practical implications, limitations, and future research directions also underlined in this study.

eResearch in acute kidney injury: a primer for electronic health record research

Acute kidney injury (AKI) has a significant impact on patient morbidity and mortality as well as overall health care costs. eResearch, which integrates information technology and information management to optimize research strategies, provides a perfect platform for necessary ongoing AKI research. With the recent adoption of a widely accepted definition of AKI and near-universal use of electronic health records, eResearch is becoming an important tool in AKI research. Conducting eResearch in AKI should ideally be based on a relatively uniform methodology. This article is the first of its kind to describe a methodology for pursuing eResearch specific to AKI and includes an illustrative database example for critically ill patients. We discuss strategies for using serum creatinine and urine output in large databases to identify and stage AKI and ways to interpolate missing values and validate data. Issues specific to the pediatric population include variation in serum creatinine with growth, varied severity of illness scoring systems and medication dosage based on weight. Many of these same strategies used to optimize AKI eResearch can be applicable to real-time AKI alerts with potential integration of additional clinical variables.

Current status of use of big data and artificial intelligence in RMDs: a systematic literature review informing EULAR recommendations

Objective

To assess the current use of big data and artificial intelligence (AI) in the field of rheumatic and musculoskeletal diseases (RMDs).

Methods

A systematic literature review was performed in PubMed MEDLINE in November 2018, with key words referring to big data, AI and RMDs. All original reports published in English were analysed. A mirror literature review was also performed outside of RMDs on the same number of articles. The number of data analysed, data sources and statistical methods used (traditional statistics, AI or both) were collected. The analysis compared findings within and beyond the field of RMDs.

Results

Of 567 articles relating to RMDs, 55 met the inclusion criteria and were analysed, as well as 55 articles in other medical fields. The mean number of data points was 746 million (range 2000–5 billion) in RMDs, and 9.1 billion (range 100 000–200 billion) outside of RMDs. Data sources were varied: in RMDs, 26 (47%) were clinical, 8 (15%) biological and 16 (29%) radiological. Both traditional and AI methods were used to analyse big data (respectively, 10 (18%) and 45 (82%) in RMDs and 8 (15%) and 47 (85%) out of RMDs). Machine learning represented 97% of AI methods in RMDs and among these methods, the most represented was artificial neural network (20/44 articles in RMDs).

Conclusions

Big data sources and types are varied within the field of RMDs, and methods used to analyse big data were heterogeneous. These findings will inform a European League Against Rheumatism taskforce on big data in RMDs.

The Importance of Reproducibility in Plastic Surgery Research

With the advent of big data and database-driven research, the need for reproducible methods has become especially relevant. Given the rise of evidence-based practice, it is crucial to ensure that findings making use of big data can be consistently replicated by other physician-scientists. A call for transparency and reproducibility must occur at the individual, institutional, and national levels. Given the rising popularity of national and large databases in research, the responsibility of authors to ensure reproducibility of clinical research merits renewed discussion. In this article, the authors offer strategies to increase clinical research reproducibility at both the individual and institutional levels, within the context of plastic surgery.

An argument for reporting data standardization procedures in multi-site predictive modeling: case study on the impact of LOINC standardization on model performance

Objectives

We aimed to gain a better understanding of how standardization of laboratory data can impact predictive model performance in multi-site datasets. We hypothesized that standardizing local laboratory codes to logical observation identifiers names and codes (LOINC) would produce predictive models that significantly outperform those learned utilizing local laboratory codes.

Materials and Methods

We predicted 30-day hospital readmission for a set of heart failure-specific visits to 13 hospitals from 2008 to 2012. Laboratory test results were extracted and then manually cleaned and mapped to LOINC. We extracted features to summarize laboratory data for each patient and used a training dataset (2008–2011) to learn models using a variety of feature selection techniques and classifiers. We evaluated our hypothesis by comparing model performance on an independent test dataset (2012).

Results

Models that utilized LOINC performed significantly better than models that utilized local laboratory test codes, regardless of the feature selection technique and classifier approach used.

Discussion and Conclusion

We quantitatively demonstrated the positive impact of standardizing multi-site laboratory data to LOINC prior to use in predictive models. We used our findings to argue for the need for detailed reporting of data standardization procedures in predictive modeling, especially in studies leveraging multi-site datasets extracted from electronic health records.

A pilot and comparative study between pathological and serological levels of immunoglobulin and complement among three kinds of primary glomerulonephritis

Background

Immunoglobulin A nephropathy (IgAN), membranous nephropathy (MN) and minimal-change disease (MCD) are three common types of glomerulonephritis in China. Pathological diagnosis based on renal biopsy is the criterion and the golden standard for diagnosing the sub-types of primary or secondary glomerulonephritis. Immunoglobulin and complements might be used in the differential diagnosis of glomerulonephritis without renal biopsies. However, the relationship between IF intensities of immune proteins and the corresponding serum levels remained unclear, and seldom studies combine histopathological examination results and blood tests together for a predictive purpose. This study was considered as a pilot study for integrating histopathological indicators into serum parameters for exploring the relationship of IF intensity and serum values of immunoglobulin and complement, and for screening and investigating effective indicators inIgAN, MN and MCD.

Methods

Renal tissue immunofluorescence (IF) intensity grades and serum levels of immunoglobulin and complements (IgG, IgA, IgM, C3 and C4) were retrospectively analyzed in 236 cases with IgAN, MN or MCD. IF grades were grouped as negative (−), positive (+) or strong positive (++) with both high and low magnification of microscope. Other serum indicators such as urea nitrogen (BUN), creatinine (Crea) and estimated glomerular filtration rate (eGFR) were also evaluated among the groups.

Results

There were difference in IgA, IgG and C3 IF intensity grades among IgAN, MN and MCD groups (p = 9.82E-43, 4.60E-39, 7.45E-15, respectively). Serum values of BUN, Crea, eGFR, IgG, IgA, IgM and C4 showed difference in three groups (BUN: p = 0.045, Crea: p = 3.45E-5, eGFR: p = 0.005, IgG: p = 1.68E-14, IgA: p = 9.14E-9, IgM: p = 0.014, C4: p = 0.026). eGFR had the trend to decrease with enhanced IgA IF positive grades (p = 8.99E-4); Crea had trends to decrease with both enhanced IgA and IgG IF intensity grades (p = 2.06E-6, 2.94E-5, respectively). In all subjects, serum IgA levels was inversely correlated with eGFR(r = − 0.216, p = 0.001) and correlated with Crea levels(r = 0.189, p = 0.004); serum IgG and Crea showed no correlation which were discordance with inverse correlation of IgG IF grade and Crea(r = 0.058,p = 0.379). IgG serum level was inverse correlated with its IF grades (p = 3.54E-5, p = 7.08E-6, respectively); C3 serum levels had significantly difference between Neg and positive (+) group (p = 0.0003). IgA serum level was positive correlated with its IF grades (Neg-(+): p = 0.0001; (+)-(++): p = 0.022; Neg-(++): p = 2.01E-10). After matching comparison among C3 groups, C3 Neg. group and C3 ++ group had difference (*p = 0.017). C4 had all negative IF expression in all pathological groups. In IgAN subjects, there were statistical differences of serum C3 levels between its pathological Neg and positive (+) group(p = 0.026), and serum IgA levels showed difference between IgA pathological positive(+) and (++)(p = 0.007). In MN subjects, sIgG levels showed difference between IgG pathological IF grade positive (+) and (++)(p = 0.044); serum C3 levels showed difference between C3 pathological IF grade Neg and positive(+)(p = 0.005); and serum IgA levels showed difference between Neg and positive(+)(p = 0.040). In IgAN, eGFR showed serum IgA levels had significant differences among groups (p = 0.007) and had increasing trend with enhanced its IF grades(P_trend = 0.016). There were also difference between IgG group Neg and positive (+) (p = 0.005, P_trend = 0.007) in IgAN. In MN, serum IgG levels had significant differences among IF groups (p = 0.034) and had decreasing trend with its enhanced IF grades (P_trend = 0.014). Serum C3 concentrations also were found distinctive among IF groups (p = 0.016) and had in inverse correlation with its enhanced IF grades (P_trend = 0.004).

Discussion

Our research cross contrasts several immunoprotein IF intensities and relevant serum levels in three kinds of primary glomerular nephritis, and finally acquired helpful results for understanding the relationships between pathological presentation and serological presentation of immunoproteins in kidney diseases. Furthermore, this pilot study is offering a possible method for the analysis of combination of pathology and serology.

Conclusion

Different pathological types of nephritis presented different expression patterns of immunoglobulin and complement, especially IgA and IgG, which suggested different pathogenesis involved in the development of IgAN and MN. Furthermore, either in tissue or in serum, increased IgA level was closely related with renal function in all of the patients.

Electronic supplementary material

The online version of this article (10.1186/s12865-018-0254-z) contains supplementary material, which is available to authorized users.

Natural Products for Drug Discovery in the 21st Century: Innovations for Novel Drug Discovery

The therapeutic properties of plants have been recognised since time immemorial. Many pathological conditions have been treated using plant-derived medicines. These medicines are used as concoctions or concentrated plant extracts without isolation of active compounds. Modern medicine however, requires the isolation and purification of one or two active compounds. There are however a lot of global health challenges with diseases such as cancer, degenerative diseases, HIV/AIDS and diabetes, of which modern medicine is struggling to provide cures. Many times the isolation of "active compound" has made the compound ineffective. Drug discovery is a multidimensional problem requiring several parameters of both natural and synthetic compounds such as safety, pharmacokinetics and efficacy to be evaluated during drug candidate selection. The advent of latest technologies that enhance drug design hypotheses such as Artificial Intelligence, the use of 'organ-on chip' and microfluidics technologies, means that automation has become part of drug discovery. This has resulted in increased speed in drug discovery and evaluation of the safety, pharmacokinetics and efficacy of candidate compounds whilst allowing novel ways of drug design and synthesis based on natural compounds. Recent advances in analytical and computational techniques have opened new avenues to process complex natural products and to use their structures to derive new and innovative drugs. Indeed, we are in the era of computational molecular design, as applied to natural products. Predictive computational softwares have contributed to the discovery of molecular targets of natural products and their derivatives. In future the use of quantum computing, computational softwares and databases in modelling molecular interactions and predicting features and parameters needed for drug development, such as pharmacokinetic and pharmacodynamics, will result in few false positive leads in drug development. This review discusses plant-based natural product drug discovery and how innovative technologies play a role in next-generation drug discovery.

Big Data Analytics in Medicine and Healthcare

This paper surveys big data with highlighting the big data analytics in medicine and healthcare. Big data characteristics: value, volume, velocity, variety, veracity and variability are described. Big data analytics in medicine and healthcare covers integration and analysis of large amount of complex heterogeneous data such as various – omics data (genomics, epigenomics, transcriptomics, proteomics, metabolomics, interactomics, pharmacogenomics, diseasomics), biomedical data and electronic health records data. We underline the challenging issues about big data privacy and security. Regarding big data characteristics, some directions of using suitable and promising open-source distributed data processing software platform are given.

Concurrence of big data analytics and healthcare: A systematic review

BACKGROUND

The application of Big Data analytics in healthcare has immense potential for improving the quality of care, reducing waste and error, and reducing the cost of care.

PURPOSE

This systematic review of literature aims to determine the scope of Big Data analytics in healthcare including its applications and challenges in its adoption in healthcare. It also intends to identify the strategies to overcome the challenges.

DATA SOURCES

A systematic search of the articles was carried out on five major scientific databases: ScienceDirect, PubMed, Emerald, IEEE Xplore and Taylor & Francis. The articles on Big Data analytics in healthcare published in English language literature from January 2013 to January 2018 were considered.

STUDY SELECTION

Descriptive articles and usability studies of Big Data analytics in healthcare and medicine were selected.

DATA EXTRACTION

Two reviewers independently extracted information on definitions of Big Data analytics; sources and applications of Big Data analytics in healthcare; challenges and strategies to overcome the challenges in healthcare.

RESULTS

A total of 58 articles were selected as per the inclusion criteria and analyzed. The analyses of these articles found that: (1) researchers lack consensus about the operational definition of Big Data in healthcare; (2) Big Data in healthcare comes from the internal sources within the hospitals or clinics as well external sources including government, laboratories, pharma companies, data aggregators, medical journals etc.; (3) natural language processing (NLP) is most widely used Big Data analytical technique for healthcare and most of the processing tools used for analytics are based on Hadoop; (4) Big Data analytics finds its application for clinical decision support; optimization of clinical operations and reduction of cost of care (5) major challenge in adoption of Big Data analytics is non-availability of evidence of its practical benefits in healthcare.

CONCLUSION

This review study unveils that there is a paucity of information on evidence of real-world use of Big Data analytics in healthcare. This is because, the usability studies have considered only qualitative approach which describes potential benefits but does not take into account the quantitative study. Also, majority of the studies were from developed countries which brings out the need for promotion of research on Healthcare Big Data analytics in developing countries.

Models and Data Sources Used in Systems Medicine

Background: Systems medicine is a new approach for the development and selection of treatment strategies for patients with complex diseases. It is often referred to as the application of systems biology methods for decision making in patient care. For systems medicine computer applications, many different data sources have to be integrated and included into models. This is a challenging task for Medical Informatics since the approach exceeds traditional systems like Electronic Health Records. To prioritize research activities for systems medicine applications, it is necessary to get an overview over modelling methods and data sources already used in this field.

Objectives: We performed a systematic literature review with the objective to capture current use of 1) modelling methods and 2) data sources in systems medicine related research projects.

Methods: We queried the MEDLINE and ScienceDirect databases for papers associated with the search term systems medicine and related terms. Papers were screened and assessed in full text in a two-step process according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement guidelines.

Results: The queries returned 698 articles of which 34 papers were finally included into the study. A multitude of modelling approaches such as machine learning and network analysis was identified and classified. Since these approaches are also used in other domains, no methods specific for systems medicine could be identified. Omics data are the most widely used data types followed by clinical data. Most studies only include a rather limited number of data sources.

Conclusions: Currently, many different modelling approaches are used in systems medicine. Thus, highly flexible modular solutions are necessary for systems medicine clinical applications. However, the number of data sources included into the models is limited and most projects currently focus on prognosis. To leverage the potential of systems medicine further, it will be necessary to focus on treatment strategies for patients and consider a broader range of data.

Machine learning approaches to personalize early prediction of asthma exacerbations

Patient telemonitoring results in an aggregation of significant amounts of information about patient disease trajectory. However, the potential use of this information for early prediction of exacerbations in adult asthma patients has not been systematically evaluated. The aim of this study was to explore the utility of telemonitoring data for building machine learning algorithms that predict asthma exacerbations before they occur. The study dataset comprised daily self-monitoring reports consisting of 7001 records submitted by adult asthma patients during home telemonitoring. Predictive modeling included preparation of stratified training datasets, predictive feature selection, and evaluation of resulting classifiers. Using a 7-day window, a naive Bayesian classifier, adaptive Bayesian network, and support vector machines were able to predict asthma exacerbation occurring on day 8, with sensitivity of 0.80, 1.00, and 0.84; specificity of 0.77, 1.00, and 0.80; and accuracy of 0.77, 1.00, and 0.80, respectively. Our study demonstrated that machine learning techniques have significant potential in developing personalized decision support for chronic disease telemonitoring systems. Future studies may benefit from a comprehensive predictive framework that combines telemonitoring data with other factors affecting the likelihood of developing acute exacerbation. Approaches implemented for advanced asthma exacerbation prediction may be extended to prediction of exacerbations in patients with other chronic health conditions.

Research Methods in Healthcare Epidemiology and Antimicrobial Stewardship: Use of Administrative and Surveillance Databases

Administrative and surveillance data are used frequently in healthcare epidemiology and antimicrobial stewardship (HE&AS) research because of their wide availability and efficiency. However, data quality issues exist, requiring careful consideration and potential validation of data. This methods paper presents key considerations for using administrative and surveillance data in HE&AS, including types of data available and potential use, data limitations, and the importance of validation. After discussing these issues, we review examples of HE&AS research using administrative data with a focus on scenarios when their use may be advantageous. A checklist is provided to help aid study development in HE&AS using administrative data.

Infect Control Hosp Epidemiol 2016;1–10

Feasibility of Population Health Analytics and Data Visualization for Decision Support in the Infectious Diseases Domain: A pilot study

OBJECTIVE

Big data or population-based information has the potential to reduce uncertainty in medicine by informing clinicians about individual patient care. The objectives of this study were: 1) to explore the feasibility of extracting and displaying population-based information from an actual clinical population's database records, 2) to explore specific design features for improving population display, 3) to explore perceptions of population information displays, and 4) to explore the impact of population information display on cognitive outcomes.

METHODS

We used the Veteran's Affairs (VA) database to identify similar complex patients based on a similar complex patient case. Study outcomes measures were 1) preferences for population information display 2) time looking at the population display, 3) time to read the chart, and 4) appropriateness of plans with pre- and post-presentation of population data. Finally, we redesigned the population information display based on our findings from this study.

RESULTS

The qualitative data analysis for preferences of population information display resulted in four themes: 1) trusting the big/population data can be an issue, 2) embedded analytics is necessary to explore patient similarities, 3) need for tools to control the view (overview, zoom and filter), and 4) different presentations of the population display can be beneficial to improve the display. We found that appropriateness of plans was at 60% for both groups (t9=-1.9; p=0.08), and overall time looking at the population information display was 2.3 minutes versus 3.6 minutes with experts processing information faster than non-experts (t8= -2.3, p=0.04).

CONCLUSION

A population database has great potential for reducing complexity and uncertainty in medicine to improve clinical care. The preferences identified for the population information display will guide future health information technology system designers for better and more intuitive display.