Advanced Data Mining Techniques Research Articles

Climate resilience in Paris: A network representation of online strategic documents released by public authorities

This study proposes to exploit recent advances in data mining techniques to examine the strategies published on the Internet by public authorities and implemented in Paris. We first conducted a qualitative review of strategic documents, released over 15 years. We then used a list of key terms concerning flood risk management to compute a semantic network and identify clusters of terms that tend to appear in similar contexts. The analysis reveals an evolution of how policy and decision-making processes are depicted on the Web. The proposed methodology can be reproduced in other cities facing climate risks.

A survey on cancer prediction and detection with data analysis

World Health Organization reports cancer as a leading cause worldwide in mortality and morbidity. Accurate and early cancer risk assessment in average- to high-risk population is vital in controlling the cancer-related suffering and mortality. Advanced bioinformatics and data mining techniques along with computer-aided cancer prediction and risk assessment are used extensively to assist in identifying the high-risk population as well as individual cancer diagnosis and treatment. An early detection minimizes the risk of cancer spreading to secondary sites and ensures appropriate treatment at the onset of the malignancy. The scope of our survey was to review over 90 publications centered around works done in the area of data analysis studies in the field of cancer prediction and detection. The motivation was to accumulate and categorize knowledge on the usage of data analytics for cancer prediction and detection. The aim was to do a comparative study of few of the major analytical approaches in cancer data analysis and highlight their effectiveness.

Rapid Screening of Complex Matrices: Utilizing Kendrick Mass Defect To Enhance Knowledge-Based Group Type Evaluation of Multidimensional Gas Chromatography-High-Resolution Time-of-Flight Mass Spectrometry Data.

Organic compound characterization of highly complex matrices involves scientific challenges, such as the diversity of "true" unknowns, the concentration ranges of various compound classes, and limited available amounts of sample. Therefore, discovery-based multidimensional gas chromatography coupled to high-resolution time-of-flight mass spectrometry (GC×GC-HRToFMS) is increasingly applied. Nevertheless, most studies focus on target analysis and tend to disregard important details of the sample composition. The increased peak or separation capacity of GC×GC-ToFMS allows for in-depth chemical analysis of the molecular composition. However, high amounts of data, containing several thousands of compounds per experiment, are generally acquired during such analyses. Coupling GC×GC to high-resolution mass spectrometry further increases the amount of data and therefore requires advanced data reduction and mining techniques. Commonly, the main approach for the evaluation of GC×GC-HRToFMS data sets either focuses on the chromatographic separation (e.g., group type analysis), or utilizes exact mass data applying Kendrick mass defect analysis or van Krevelen plots. The presented approach integrates the accurate mass data and the chromatographic information by combining Kendrick mass defect information and knowledge-based rules. This combination allows for fast, visual data screening as well as quantitative estimation of the sample's composition. Moreover, the resulting sample classification significantly reduces the number of variables, allowing distinct chemometric analysis in nontargeted studies, such as detailed hydrocarbon analyses and environmental and forensic investigations.

Using a Rule Developing Experimentation Approach to Study Social Problems

This article presents the first in a series of studies on the corruption of various types, assessed through an online experiment known as mind genomics. The data allows for the creation of simple models from regression, showing the part-worth contribution of every element to perceived corruption, and to perceived positive, neutral or negative emotion. The authors use ordinary least squares regression models and advanced data mining techniques to analyze the data and classify the users accordingly. They present the results from four countries (Albania, Hungary, India, and the USA), looking at the linkages between corruption by country, and by other factors such as social class. Based on the collected data a model is generated for each group (country, type of person), showing how the person in the group is likely to call a description ‘corrupt,' and how each particular element from the set of 20 elements related to education adds or subtracts to that basic proclivity to call a situation or behavior corrupt.

A machine learning approach to detect crude oil contamination in a real scenario using hyperspectral remote sensing

One of the most ubiquitous and detrimental types of environmental contamination in the world is crude oil pollution. When released into either the aquatic or terrestrial environments, this pollution can negatively impact flora and fauna, as well as human health. Hence, a rapid and affordable spatial assessment of the pollution is favored to limit the spill’s effects. Using airborne hyperspectral remote sensing (HRS) for crude oil detection in terrestrial areas has been investigated in previous studies, which mainly relied on heavily oiled artificial samples. These studies and others based their methodologies on the premise that the spectral features of petroleum hydrocarbon (PHC) are clearly observable, which might not be true in all cases. In this study, we aimed at assessing the true potential of using HRS for terrestrial oil spill mapping in a real disaster site in southern Israel, where laboratory and controlled conditions do not apply. Using the AISA SPECIM Fenix1 K sensor, we collected airborne image of the study site and analyzed the data with advanced data mining techniques. Various challenges and limitations arose from the airborne HRS image being taken two and a half years after the crude oil had been released into the environment and exposed to the surface. Here, no spectral features of PHC were detectable in the spectrum, preventing the use of PHC indices and spectral methods developed by others. Nevertheless, by using standardization techniques, vicarious band selection, dimension reduction, multivariate calibration, and supervised machine-learning, we were able to successfully distinguish between contaminated pixels from non-contaminated ones. Classification accuracy metrics of overall accuracy, sensitivity, specificity, and Kappa yielded good results of 0.95, 0.95, 0.95 and 0.9, respectively, for cross-validation, and 0.93, 0.91, 0.94 and 0.85, for the validation dataset. Classified image and test scenes also showed strong agreement with an orthophoto image taken several days after the disaster, when the pollution was clearly visible. Thus, we conclude that HRS technology can detect PHC traces in an oil spill site, even under the most challenging conditions.

A Weighted Voting Ensemble Self-Labeled Algorithm for the Detection of Lung Abnormalities from X-Rays

During the last decades, intensive efforts have been devoted to the extraction of useful knowledge from large volumes of medical data employing advanced machine learning and data mining techniques. Advances in digital chest radiography have enabled research and medical centers to accumulate large repositories of classified (labeled) images and mostly of unclassified (unlabeled) images from human experts. Machine learning methods such as semi-supervised learning algorithms have been proposed as a new direction to address the problem of shortage of available labeled data, by exploiting the explicit classification information of labeled data with the information hidden in the unlabeled data. In the present work, we propose a new ensemble semi-supervised learning algorithm for the classification of lung abnormalities from chest X-rays based on a new weighted voting scheme. The proposed algorithm assigns a vector of weights on each component classifier of the ensemble based on its accuracy on each class. Our numerical experiments illustrate the efficiency of the proposed ensemble methodology against other state-of-the-art classification methods.

Predicting Micro-Enterprise Failures Using Data Mining Techniques

Research analysis of small enterprises are still rare, due to lack of individual level data. Small enterprise failures are connected not only with their financial situation abut also with non-financial factors. In recent research we tend to apply more and more complex models. However, it is not so obvious that increasing complexity increases the effectiveness. In this paper the sample of 806 small enterprises were analyzed. Qualitative factors were used in modeling. Some simple and more complex models were estimated, such as logistic regression, decision trees, neural networks, gradient boosting, and support vector machines. Two hypothesis were verified: (i) not only financial ratios but also non-financial factors matter for small enterprise survival, and (ii) advanced statistical models and data mining techniques only insignificantly increase the prediction accuracy of small enterprise failures. Results show that simple models are as good as more complex model. Data mining models tend to be overfitted. Most important financial ratios in predicting small enterprise failures were: operating profitability of assets, current assets turnover, capital ratio, coverage of short-term liabilities by equity, coverage of fixed assets by equity, and the share of net financial surplus in total liabilities. Among non-financial factors only two of them were important: the sector of activity and employment.

Augmenting geovisual analytics of social media data with heterogeneous information network mining-Cognitive plausibility assessment.

This paper investigates the feasibility, from a user perspective, of integrating a heterogeneous information network mining (HINM) technique into SensePlace3 (SP3), a web-based geovisual analytics environment. The core contribution of this paper is a user study that determines whether an analyst with minimal background can comprehend the network data modeling metaphors employed by the resulting system, whether they can employ said metaphors to explore spatial data, and whether they can interpret the results of such spatial analysis correctly. This study confirms that all of the above is, indeed, possible, and provides empirical evidence about the importance of a hands-on tutorial and a graphical approach to explaining data modeling metaphors in the successful adoption of advanced data mining techniques. Analysis of outcomes of data exploration by the study participants also demonstrates the kinds of insights that a visual interface to HINM can enable. A second contribution is a realistic case study that demonstrates that our HINM approach (made accessible through a visual interface that provides immediate visual feedback for user queries), produces a clear and a positive difference in the outcome of spatial analysis. Although this study does not aim to validate HINM as a data modeling approach (there is considerable evidence for this in existing literature), the results of the case study suggest that HINM holds promise in the (geo)visual analytics domain as well, particularly when integrated into geovisual analytics applications. A third contribution is a user study protocol that is based on and improves upon the current methodological state of the art. This protocol includes a hands-on tutorial and a set of realistic data analysis tasks. Detailed evaluation protocols are rare in geovisual analytics (and in visual analytics more broadly), with most studies reviewed in this paper failing to provide sufficient details for study replication or comparison work.

A random forest partition model for predicting NO2 concentrations from traffic flow and meteorological conditions

High concentrations of nitrogen dioxide in the air, particularly in heavily urbanised areas, have an adverse effect on many aspects of residents' health (short-term and long-term damage, unpleasant odour and other). A method is proposed for modelling atmospheric NO2 concentrations in a conurbation, using a partition model M consisting of two separate models: ML for lower concentration values and MU for upper values. An advanced data mining technique, that of random forests, is used. This is a method based on machine learning, involving the simultaneous compilation of information from multiple random trees. Using the example of data recorded in Wrocław (Poland) in 2015–2017, an iterative method was applied to determine the boundary concentration y˜ for which the mean absolute deviation error for the partition model attained its lowest value. The resulting model had an R2 value of 0.82, compared with 0.60 for a classical random forest model. The importances of the variables in the model ML, similarly as in the classical case, indicate that the greatest influence on NO2 concentrations comes from traffic flow, followed by meteorological factors, in particular the wind direction and speed. In the model MU the importances of the variables are significantly different: while traffic flow still has the greatest impact, the effects of temperature and relative humidity are almost as great. This confirms the justifiability of constructing separate models for low and high pollution concentrations.

Advanced data mining approaches in the assessment of urinary concentrations of bisphenols, chlorophenols, parabens and benzophenones in Brazilian children and their association to DNA damage

Human exposure to endocrine disrupting chemicals (EDCs) has received considerable attention over the last three decades. However, little is known about the influence of co-exposure to multiple EDCs on effect-biomarkers such as oxidative stress in Brazilian children. In this study, concentrations of 40 EDCs were determined in urine samples collected from 300 Brazilian children of ages 6–14 years and data were analyzed by advanced data mining techniques. Oxidative DNA damage was evaluated from the urinary concentrations of 8-hydroxy-2′-deoxyguanosine (8OHDG). Fourteen EDCs, including bisphenol A (BPA), methyl paraben (MeP), ethyl paraben (EtP), propyl paraben (PrP), 3,4-dihydroxy benzoic acid (3,4-DHB), methyl-protocatechuic acid (OH-MeP), ethyl-protocatechuic acid (OH-EtP), triclosan (TCS), triclocarban (TCC), 2-hydroxy-4-methoxybenzophenone (BP3), 2,4-dihydroxybenzophenone (BP1), bisphenol A bis(2,3-dihydroxypropyl) glycidyl ether (BADGE·2H2O), 2,4-dichlorophenol (2,4-DCP), and 2,5-dichlorophenol (2,5-DCP) were found in >50% of the urine samples analyzed. The highest geometric mean concentrations were found for MeP (43.1 ng/mL), PrP (3.12 ng/mL), 3,4-DHB (42.2 ng/mL), TCS (8.26 ng/mL), BP3 (3.71 ng/mL), and BP1 (4.85 ng/mL), and exposures to most of which were associated with personal care product (PCP) use. Statistically significant associations were found between urinary concentrations of 8OHDG and BPA, MeP, 3,4-DHB, OH-MeP, OH-EtP, TCS, BP3, 2,4-DCP, and 2,5-DCP. After clustering the data on the basis of i) 14 EDCs (exposure levels), ii) demography (age, gender and geographic location), and iii) 8OHDG (effect), two distinct clusters of samples were identified. 8OHDG concentration was the most critical parameter that differentiated the two clusters, followed by OH-EtP. When 8OHDG was removed from the dataset, predictability of exposure variables increased in the order of: OH-EtP > OH-MeP > 3,4-DHB > BPA > 2,4-DCP > MeP > TCS > EtP > BP1 > 2,5-DCP. Our results showed that co-exposure to OH-EtP, OH-MeP, 3,4-DHB, BPA, 2,4-DCP, MeP, TCS, EtP, BP1, and 2,5-DCP was associated with DNA damage in children. This is the first study to report exposure of Brazilian children to a wide range of EDCs and the data mining approach further strengthened our findings of chemical co-exposures and biomarkers of effect.

Research and Applications of Data Mining Techniques for Improving Building Operational Performance

This paper reviews the data mining (DM)-related research and applications at the building operation stage. It aims to summarize DM-based solutions for building energy management and reveal current research and development outcomes in analyzing massive building operational data using advanced DM techniques. Previous studies mainly adopt DM techniques for two tasks, i.e., (1) predictive modeling; (2) fault detection and diagnosis. The knowledge discovered has been successfully utilized to facilitate the decision-making during building operations. Domain expertise play the dominant role in the knowledge discovery process, which limits the chance of discovering novel knowledge. DM is a promising technology for the development of intelligent and automated building management systems. Despite encouraging results, more research efforts should be made in (1) exploring the usefulness of unsupervised DM, (2) developing generic analytic frameworks, and (3) analyzing unstructured and multi-relational data sets.

MSL: Facilitating automatic and physical analysis of published scientific literature in PDF format

Published scientific literature contains millions of figures, including information about the results obtained from different scientific experiments e.g. PCR-ELISA data, microarray analysis, gel electrophoresis, mass spectrometry data, DNA/RNA sequencing, diagnostic imaging (CT/MRI and ultrasound scans), and medicinal imaging like electroencephalography (EEG), magnetoencephalography (MEG), echocardiography (ECG), positron-emission tomography (PET) images. The importance of biomedical figures has been widely recognized in scientific and medicine communities, as they play a vital role in providing major original data, experimental and computational results in concise form. One major challenge for implementing a system for scientific literature analysis is extracting and analyzing text and figures from published PDF files by physical and logical document analysis. Here we present a product line architecture based bioinformatics tool ‘Mining Scientific Literature (MSL)’, which supports the extraction of text and images by interpreting all kinds of published PDF files using advanced data mining and image processing techniques. It provides modules for the marginalization of extracted text based on different coordinates and keywords, visualization of extracted figures and extraction of embedded text from all kinds of biological and biomedical figures using applied Optimal Character Recognition (OCR). Moreover, for further analysis and usage, it generates the system’s output in different formats including text, PDF, XML and images files. Hence, MSL is an easy to install and use analysis tool to interpret published scientific literature in PDF format.

MSL: Facilitating automatic and physical analysis of published scientific literature in PDF format.

Published scientific literature contains millions of figures, including information about the results obtained from different scientific experiments e.g. PCR-ELISA data, microarray analysis, gel electrophoresis, mass spectrometry data, DNA/RNA sequencing, diagnostic imaging (CT/MRI and ultrasound scans), and medicinal imaging like electroencephalography (EEG), magnetoencephalography (MEG), echocardiography (ECG), positron-emission tomography (PET) images. The importance of biomedical figures has been widely recognized in scientific and medicine communities, as they play a vital role in providing major original data, experimental and computational results in concise form. One major challenge for implementing a system for scientific literature analysis is extracting and analyzing text and figures from published PDF files by physical and logical document analysis. Here we present a product line architecture based bioinformatics tool 'Mining Scientific Literature (MSL)', which supports the extraction of text and images by interpreting all kinds of published PDF files using advanced data mining and image processing techniques. It provides modules for the marginalization of extracted text based on different coordinates and keywords, visualization of extracted figures and extraction of embedded text from all kinds of biological and biomedical figures using applied Optimal Character Recognition (OCR). Moreover, for further analysis and usage, it generates the system's output in different formats including text, PDF, XML and images files. Hence, MSL is an easy to install and use analysis tool to interpret published scientific literature in PDF format.

The Ocean Carbon States Database: a proof-of-concept application of cluster analysis in the ocean carbon cycle

Abstract. In this paper, we present a database of the basic regimes of the carbon cycle in the ocean, the “ocean carbon states”, as obtained using a data mining/pattern recognition technique in observation-based as well as model data. The goal of this study is to establish a new data analysis methodology, test it and assess its utility in providing more insights into the regional and temporal variability of the marine carbon cycle. This is important as advanced data mining techniques are becoming widely used in climate and Earth sciences and in particular in studies of the global carbon cycle, where the interaction of physical and biogeochemical drivers confounds our ability to accurately describe, understand, and predict CO2 concentrations and their changes in the major planetary carbon reservoirs. In this proof-of-concept study, we focus on using well-understood data that are based on observations, as well as model results from the NASA Goddard Institute for Space Studies (GISS) climate model. Our analysis shows that ocean carbon states are associated with the subtropical–subpolar gyre during the colder months of the year and the tropics during the warmer season in the North Atlantic basin. Conversely, in the Southern Ocean, the ocean carbon states can be associated with the subtropical and Antarctic convergence zones in the warmer season and the coastal Antarctic divergence zone in the colder season. With respect to model evaluation, we find that the GISS model reproduces the cold and warm season regimes more skillfully in the North Atlantic than in the Southern Ocean and matches the observed seasonality better than the spatial distribution of the regimes. Finally, the ocean carbon states provide useful information in the model error attribution. Model air–sea CO2 flux biases in the North Atlantic stem from wind speed and salinity biases in the subpolar region and nutrient and wind speed biases in the subtropics and tropics. Nutrient biases are shown to be most important in the Southern Ocean flux bias. All data and analysis scripts are available at https://data.giss.nasa.gov/oceans/carbonstates/ (DOI: https://doi.org/10.5281/zenodo.996891).

Effective heart disease prediction system using data mining techniques.

The health care industries collect huge amounts of data that contain some hidden information, which is useful for making effective decisions. For providing appropriate results and making effective decisions on data, some advanced data mining techniques are used. In this study, an effective heart disease prediction system (EHDPS) is developed using neural network for predicting the risk level of heart disease. The system uses 15 medical parameters such as age, sex, blood pressure, cholesterol, and obesity for prediction. The EHDPS predicts the likelihood of patients getting heart disease. It enables significant knowledge, eg, relationships between medical factors related to heart disease and patterns, to be established. We have employed the multilayer perceptron neural network with backpropagation as the training algorithm. The obtained results have illustrated that the designed diagnostic system can effectively predict the risk level of heart diseases.

Programming models and systems for Big Data analysis

ABSTRACTBig Data analysis refers to advanced and efficient data mining and machine learning techniques applied to large amount of data. Research work and results in the area of Big Data analysis are continuously rising, and more and more new and efficient architectures, programming models, systems, and data mining algorithms are proposed. Taking into account the most popular programming models for Big Data analysis (MapReduce, Directed Acyclic Graph, Message Passing, Bulk Synchronous Parallel, Workflow and SQL-like), we analysed the features of the main systems implementing them. Such systems are compared using four classification criteria (i.e. level of abstraction, type of parallelism, infrastructure scale and classes of applications) for helping developers and users to identify and select the best solution according to their skills, hardware availability, productivity and application needs.

AN ALGORITHM FOR PREDICTIVE DATA MINING APPROACH IN MEDICAL DIAGNOSIS

The Healthcare industry contains big and complex data that may be required in order to discover fascinating pattern of diseases & makes effective decisions with the help of different machine learning techniques. Advanced data mining techniques are used to discover knowledge in database and for medical research. This paper has analyzed prediction systems for Diabetes, Kidney and Liver disease using more number of input attributes. The data mining classification techniques, namely Support Vector Machine (SVM) and Random Forest (RF) are analyzed on Diabetes, Kidney and Liver disease database. The performance of these techniques is compared, based on precision, recall, accuracy, f_measure as well as time. As a result of study the proposed algorithm is designed using SVM and RF algorithm and the experimental result shows the accuracy of 99.35%, 99.37 and 99.14 on diabetes, kidney and liver disease respectively.

A novel method for predicting kidney stone type using ensemble learning.

The high morbidity rate associated with kidney stone disease, which is a silent killer, is one of the main concerns in healthcare systems all over the world. Advanced data mining techniques such as classification can help in the early prediction of this disease and reduce its incidence and associated costs. The objective of the present study is to derive a model for the early detection of the type of kidney stone and the most influential parameters with the aim of providing a decision-support system. Information was collected from 936 patients with nephrolithiasis at the kidney center of the Razi Hospital in Rasht from 2012 through 2016. The prepared dataset included 42 features. Data pre-processing was the first step toward extracting the relevant features. The collected data was analyzed with Weka software, and various data mining models were used to prepare a predictive model. Various data mining algorithms such as the Bayesian model, different types of Decision Trees, Artificial Neural Networks, and Rule-based classifiers were used in these models. We also proposed four models based on ensemble learning to improve the accuracy of each learning algorithm. In addition, a novel technique for combining individual classifiers in ensemble learning was proposed. In this technique, for each individual classifier, a weight is assigned based on our proposed genetic algorithm based method. The generated knowledge was evaluated using a 10-fold cross-validation technique based on standard measures. However, the assessment of each feature for building a predictive model was another significant challenge. The predictive strength of each feature for creating a reproducible outcome was also investigated. Regarding the applied models, parameters such as sex, acid uric condition, calcium level, hypertension, diabetes, nausea and vomiting, flank pain, and urinary tract infection (UTI) were the most vital parameters for predicting the chance of nephrolithiasis. The final ensemble-based model (with an accuracy of 97.1%) was a robust one and could be safely applied to future studies to predict the chances of developing nephrolithiasis. This model provides a novel way to study stone disease by deciphering the complex interaction among different biological variables, thus helping in an early identification and reduction in diagnosis time.

Detection and Evaluation of Spatio-Temporal Spike Patterns in Massively Parallel Spike Train Data with SPADE

Repeated, precise sequences of spikes are largely considered a signature of activation of cell assemblies. These repeated sequences are commonly known under the name of spatio-temporal patterns (STPs). STPs are hypothesized to play a role in the communication of information in the computational process operated by the cerebral cortex. A variety of statistical methods for the detection of STPs have been developed and applied to electrophysiological recordings, but such methods scale poorly with the current size of available parallel spike train recordings (more than 100 neurons). In this work, we introduce a novel method capable of overcoming the computational and statistical limits of existing analysis techniques in detecting repeating STPs within massively parallel spike trains (MPST). We employ advanced data mining techniques to efficiently extract repeating sequences of spikes from the data. Then, we introduce and compare two alternative approaches to distinguish statistically significant patterns from chance sequences. The first approach uses a measure known as conceptual stability, of which we investigate a computationally cheap approximation for applications to such large data sets. The second approach is based on the evaluation of pattern statistical significance. In particular, we provide an extension to STPs of a method we recently introduced for the evaluation of statistical significance of synchronous spike patterns. The performance of the two approaches is evaluated in terms of computational load and statistical power on a variety of artificial data sets that replicate specific features of experimental data. Both methods provide an effective and robust procedure for detection of STPs in MPST data. The method based on significance evaluation shows the best overall performance, although at a higher computational cost. We name the novel procedure the spatio-temporal Spike PAttern Detection and Evaluation (SPADE) analysis.

Smart Devices for Older Adults Managing Chronic Disease: A Scoping Review.

BackgroundThe emergence of smartphones and tablets featuring vastly advancing functionalities (eg, sensors, computing power, interactivity) has transformed the way mHealth interventions support chronic disease management for older adults. Baby boomers have begun to widely adopt smart devices and have expressed their desire to incorporate technologies into their chronic care. Although smart devices are actively used in research, little is known about the extent, characteristics, and range of smart device-based interventions.ObjectiveWe conducted a scoping review to (1) understand the nature, extent, and range of smart device-based research activities, (2) identify the limitations of the current research and knowledge gap, and (3) recommend future research directions.MethodsWe used the Arksey and O’Malley framework to conduct a scoping review. We identified relevant studies from MEDLINE, Embase, CINAHL, and Web of Science databases using search terms related to mobile health, chronic disease, and older adults. Selected studies used smart devices, sampled older adults, and were published in 2010 or after. The exclusion criteria were sole reliance on text messaging (short message service, SMS) or interactive voice response, validation of an electronic version of a questionnaire, postoperative monitoring, and evaluation of usability. We reviewed references. We charted quantitative data and analyzed qualitative studies using thematic synthesis. To collate and summarize the data, we used the chronic care model.ResultsA total of 51 articles met the eligibility criteria. Research activity increased steeply in 2014 (17/51, 33%) and preexperimental design predominated (16/50, 32%). Diabetes (16/46, 35%) and heart failure management (9/46, 20%) were most frequently studied. We identified diversity and heterogeneity in the collection of biometrics and patient-reported outcome measures within and between chronic diseases. Across studies, we found 8 self-management supporting strategies and 4 distinct communication channels for supporting the decision-making process. In particular, self-monitoring (38/40, 95%), automated feedback (15/40, 38%), and patient education (13/40, 38%) were commonly used as self-management support strategies. Of the 23 studies that implemented decision support strategies, clinical decision making was delegated to patients in 10 studies (43%). The impact on patient outcomes was consistent with studies that used cellular phones. Patients with heart failure and asthma reported improved quality of life. Qualitative analysis yielded 2 themes of facilitating technology adoption for older adults and 3 themes of barriers.ConclusionsLimitations of current research included a lack of gerontological focus, dominance of preexperimental design, narrow research scope, inadequate support for participants, and insufficient evidence for clinical outcome. Recommendations for future research include generating evidence for smart device-based programs, using patient-generated data for advanced data mining techniques, validating patient decision support systems, and expanding mHealth practice through innovative technologies.