Sage Journals: Discover world-class research

Abstract

Supporting clinicians in decision making using advanced technologies has been an active research area in biomedical engineering during the past years. Among a wide range of ubiquitous systems, smartphone applications have been increasingly developed in healthcare settings to help clinicians as well as patients. Today, many smartphone applications, from basic data analysis to advanced patient monitoring, are available to clinicians and patients. Such applications are now increasingly integrating into healthcare for clinical decision support, and therefore, concerns around accuracy, stability, and dependency of these applications are rising. In addition, lack of attention to the clinicians’ acceptability, as well as the low impact on the medical professionals’ decision making, are posing more serious issues on the acceptability of smartphone applications. This article reviews smartphone-based decision support applications, focusing on hospital care settings and their overall impact of these applications on the wider clinical workflow. Additionally, key challenges and barriers of the current ubiquitous device-based healthcare applications are identified. Finally, this article addresses current challenges, future directions, and the adoption of mobile healthcare applications.

Keywords

decision support systems healthcare applications smartphone applications ubiquitous devices in healthcare

Introduction

Ubiquitous devices such as tablets and smartphones, which are gaining more attention in every aspect of human life, are also playing an important role in healthcare delivery.¹ Smartphones provide the high computing power of a personal computer as well as the wireless connectivity of a mobile. Moreover, they are compact and have fast processing features and several in-built sensors, making them suitable for use in the healthcare setting. They can be employed for patient administration, billing, health information, making appointments, monitoring of laboratory results, and clinical decision support (CDS). It is beyond the scope of this review to cover all ubiquitous devices and applications in healthcare; instead, the focus will be on decision support and patient monitoring applications (apps) in hospital care settings.^2,3

Mobile healthcare apps can be seen as the future of low-cost ubiquitous devices in healthcare and can be categorized as portable or data logging devices. Usually, the portable or wearable devices operate in conjunction with wireless body area networks or wireless personal area networks, as available communication technologies/medium. Additionally, apps for data logging medical devices (consumer and/or hospital grade) usually work with Bluetooth (BT) and wireless sensor networks for device-to-device integration to collate raw data from the human body using portable sensors.^4,5

CDS apps are facing challenges in providing up-to-date and accurate information continuously at the point-of-care for clinical decision making. This becomes even more complex when there is no single best option and/or when decisions are based on real-time and patient-centered care.^2,3,6

The success of smartphone-based CDS apps in hospital care settings is still debatable.⁷ There are limited studies regarding the successful implementation and/or clinically trailed apps in wider hospital care settings. However, there are reports on the design, development (prototype), and accuracy (by simulation) in hospital care as well as other clinical and non-clinical settings, which lack system-related issues such as implementation, consultation, and user accessibility. Providing smartphone-based CDS is a challenging task, due to the limitations specific to mobile platform, interoperability application development, and various device–data integrations.⁷

Materials and methods

An extensive search has been carried using major academic research databases, comprising Scopus, SpringerLink, IEEE Xplore, and PubMed for articles related to “smartphone healthcare,” “mobile healthcare,” “tablet health monitoring,” and “smartphone CDS apps.” We considered papers that discussed technical design, innovation, evaluation, or use of smartphones for healthcare professionals in hospital care settings and limited to “mobile decision support systems,” “ubiquitous devices,” and “ubiquitous healthcare systems.” Studies involving “tablet” related to medication were removed from the research. The search for articles was limited to “hospital” or “hospital care” or “secondary healthcare” or “smartphone health applications.” Articles dealing with advanced technologies and innovative methodologies, especially those focused on CDS, were considered. Furthermore, studies dealing with in-built sensors/feature applications within the CDS area were also included. Initially, the search yielded 76 articles, but 10 reviews and 44 articles (general sensing, fitness, activity, and non-hospital) were excluded. Finally, 22 potential studies from 2014 to 2016 were selected for this review based on the above inclusion and exclusion criteria.

Smartphone-based CDS applications

Smartphones are emerging as evidence-based tools designed to reduce clinical workflow and assist with clinician decision making and patient participation.⁸ The International Patient Decision Aids Standards (IPDAS) has identified key components and standards of a high-quality patient decision aid.⁹ Four basic features of most smartphone apps include (1) data sharing; (2) data organization (alerts, reminders, and history); (3) decision support/interpretation; and (4) user knowledge and support. These features of smartphone apps can be enhanced by integrating electronic patient health records into various mobile devices.¹⁰

Four major areas of an overall healthcare system are key to enabling successful CDS applications (Figure 1).^1,8,11,12 These areas are (1) structured information that includes standard and structured data (clinical information) such as coded problems of a patient available in the patient record, (2) information exchange that includes vast areas of cross-platform availability of various apps, (3) transformation that includes digital transformation from the traditional/manual methods, and (4) data analysis that interprets raw data into meaningful and actionable data via a smartphone application for supporting clinicians to make better decisions.

Figure 1.

The four key areas required for efficient and functional smartphone CDS applications.

Structured information for mHealth applications

Digital health technologies, including electronic medical records (EMRs), imaging, e-prescribing and the increasingly prevalent use of connected devices to monitor health, have the potential to generate large amounts of data that could be of considerable benefit to researchers and policymakers if the data could be structured and coded.

CDS apps make use of the structured and coded data to assist clinicians by providing evidence so that they can make better and informed point-of-care decision. There are three processes required to achieve these benefits: unlocking value in EMRs, new forms of access that allow patients direct control, and pervasive computing and connected devices (m-health) to enable expansion of the “real-time” patient data. Unfortunately, reviewing tailored information with each patient is costly in terms of time and resources.¹¹ In an attempt to engage clinicians and patients during their hospital stay, a tablet application was developed to provide interactive information to patients.^13,14 The application focused on providing the clinicians with meaningful data to make better decisions instead of pushing raw data which is of no use to the clinicians.^13,14

Moreover, ubiquitous devices are useful to the clinicians if they provide the required flexibility and adaptability.⁵ The exponential growth of the Internet, the application of smartphones in our daily lives, and the deployment of 4G networks should result in the provision of higher quality of healthcare services. However, the majority of the reviewed apps focused on data analysis, and on one specific, and/or early detection using complex gadgets, making these apps inefficient in non-specialized consultations. It is recommended that mobile apps need to be integrated with the electronic health records (EHRs), cloud storage, or data mining systems to multiply their efficiency and significantly improve the overall clinical outcome.¹⁵

Digital transformation for CDS applications

In the contemporary era, digital technologies have become increasingly ubiquitous across all social institutions. The emergence of mobile digital devices such as smartphones, tablet computers, and wearable devices enables collection of massive digital datasets, knowledge production, and data mining. Manual article/hard copy–based “tools” and “scales” are being automated with easy to use graphical user interface (GUI) via smartphone apps to integrate advanced technologies into medical settings. For example, a smartphone wound care application¹⁶ was developed to replicate the paper-based pressure ulcer scale for healing (PUSH tool),¹⁷ Braden scale,¹⁸ and the Bates-Jensen tool.¹⁹ This system automated the existing tools and allowed clinicians create, view, access, delete, and re-assess patient records relating to wound care. Critical design considerations were given to the smartphone application, such as simplifying GUI, minimizing visual elements on any given screen to reduce clutter, and using color cues to focus information and converge critical information. The number of steps to complete a common task related to wound care were also significantly reduced using mobile tools. The application was developed for a Nexus 4 smartphone and Nexus 7 tablet and tested by eight nurses with an age range of 31–60 years. There was a very strong perceived correlation between the paper-based forms and the wound care application in terms of content and data entry expectations, with scores of 4.60/5.00 for the Braden Scale and 4.57/5.00 for the PUSH tool.¹⁶

Future CDS apps must leverage existing capabilities from the sophisticated features (hardware and software) of the ubiquitous devices and integrate them with electronic patient health records.²⁰ Healthcare information could be uploaded to the cloud where observations from various ubiquitous devices would be integrated.²¹ By utilizing data analytics and machine learning techniques, visualized trends or patterns embedded in massive data collected in parallel at runtime from millions of mobile devices could be explored for accurate and timely decision support.^22,23 Smartphones, in contrast to personal computers, allow much needed “flexibility.” They are also characterized by mobility due to their size and weight, intuitive handling through touchscreen and gesture navigation, and low barriers relating to their operations and maintenance.²⁴ They offer an innovative concept of software delivery and offer state-of-the-art methods for service design and delivery in an organizational context. Smartphone’s advanced built-in sensors and features are understood to be one of the driving forces toward the global adoption of such technology in hospital care.²⁵

Data analysis using smartphone applications

The rapid emergence of apps, combined with the relative low-cost, high processing speed, and power of real-time data analysis, has resulted in the mHealth application adoption.⁸ Data analysis and data interpretation techniques can be applied to provide insights for clinicians.

The high-resolution display of the tablet (Apple’s iPad™) performed equally to conventional desktop liquid crystal display (LCD) monitors in preliminary interpretation of emergent computed tomography (CT) brain exams after minor modifications were made to the tablet’s zoom function capabilities.²⁶ Sterile tablet computers have been successfully utilized in the operating room by neurosurgeons as a substitute for expensive commercial intraoperative imaging equipment for image guidance during tumor resection procedures. Another study found internal medicine residents (junior doctors) felt subjectively more efficient on the wards when they were provided with ubiquitous devices (iPad tablets) loaded with the hospital EMR access programme.¹²

Sclafani et al.²⁷ reported that both tablet-owning and non-tablet owning physicians viewed the tablet computer as a useful educational utility and endorsed integration of the device into clinical practice and medical education/decision making. It is quite early to establish the success of smartphone application (especially their decision support capabilities) in hospital care settings. However, the literature suggests that mobile healthcare apps (using ubiquitous devices) are fast emerging as a decision support tool for clinicians in acute care settings.²⁷

Doty et al.²⁸ outlined a wrist-worn integrated health monitoring device that collected data from six bio-signals measuring, including fall detection, electrocardiogram (ECG), blood pressure, pulse oximetry (SpO2), respiration rate, and body surface temperature. This solution provided real-time information of the patient’s condition, such as vital bio-signals and location information. The developed system provided rapid and appropriate directions in emergency situations and alerted the user or caregiver to manage the changes in the patient’s health condition.^28,29

In one study,³⁰ the authors proposed a system on falls prevention, detection, and biofeedback monitoring using ubiquitous devices. The system used infrared sensors or vision cameras to detect falls. It included a three-axis accelerometer motion system and smart shoes. The signals were measured and processed by a mobile device, allowing the analysis and diagnosis of the routine ambient-assisted living (AAL). To improve the accuracy of the proposed application, a frequency-adaptive sensor fusion method and a kinematic model were utilized to construct the whole-body motion in real time and were continuously updated for optimization. Starostenko et al.³¹ described a system with four sensors, including ECG, three-axis accelerometer, temperature, and tight-switch, which enabled remote monitoring. The ECG, measured with wearable electrodes, used steel textile to generate the real-time heart-rate estimator. The tight-switch sensor and filter impulse response (FIR) filter technology were applied to get the best heart-rate accuracy. Moreover, the device had low-power consumption to transmit detected bio-information from these four sensors. Such transmission makes this device highly suitable for apps such as remote healthcare and wellness monitoring.³¹ Table 1 summarizes ubiquitous healthcare systems with CDS features.

Table 1.

Ubiquitous healthcare systems with clinical decision support (CDS) features.

Application	CDS function	Platform/devices	Outcome
Starostenko et al.³¹	Real-time ECG monitoring and heart-rate accuracy	Ubiquitous devices (smartphone and tablet)	A low-power consumption to transmit detected bio-information from four sensors
Horta et al.³⁰	The analysis and diagnosis of ambient-assisted living (AAL)	Ubiquitous devices (smartphone and tablet)	Falls prevention and detection and biofeedback monitoring systems using ubiquitous devices
Sclafani et al.²⁷	Various decision support	Ubiquitous devices (smartphone and tablet) including computer/desktop	Clinical education
Doty et al.²⁸	Measuring six bio-signals, includes fall detection, ECG, blood pressure, pulse oximetry (SpO2), respiration rate, and body surface temperature	Smartphone device	A wrist-worn integrated health monitoring device
Dexheimer and Borycki²⁶	Image analysis of CT-brain in an emergency department	Apple’s iPad™	CT Brain image analysis

ECG: electrocardiogram; CT: computed tomography.

Current issues and challenges of smartphone applications in hospital care settings

In the past 30 years, there have been significant advances toward decision support tools, initially with paper-based manual tools, scales, scores, and charts gradually transferred into computerized and semi-automated systems.³² Currently, emerging mHealth apps are being fully integrated with the EHR systems to support clinicians in their decision making. Despite the significant advances in decision support technologies, there are still gaps remain that prevent the wider adoption in healthcare settings.³³ Health innovations using the latest technologies and techniques offer great advantages, but at the same time, they pose security and privacy threats to the patients’ personal information, clinician and end-user acceptability, data storage, data access, and data organization and processing.⁶ In addition, data processing on a local device impacts the device’s battery life, and this is currently one of its greatest drawbacks.³⁴

In the context of this review, we sought to identify critical issues related to decision support systems. Therefore, we excluded common smartphone-/tablet-related issues which have been previously extensively covered by other researchers, for example, power consumption,² battery life,^35,36 user acceptance,³⁷ and clinical data security and privacy.^3,38 Instead, we focused on issues related to decision support capability and their acceptance in hospital care settings, data processing and analysis,^39,40 and information exchange, as required for optimal integration of mHealth apps. Smartphone apps and their issues and challenges are shown in Figure 2. The major issues and challenges can be categorized into four main divisions: (1) clinician/user consultation, (2) transmission and processing, (3) data integration, and (4) design and development, as discussed below.

Figure 2.

Smartphone applications and their issues and challenges.

Data processing and “big” data analysis

Medical standards compel the use of high-quality data in mHealth apps for high accuracy and reliable communications.⁴¹ Various techniques have been applied to collect high-quality health data.^7,42,43 Examples include a novel unbiased and normalized adaptive noise reduction application to suppress random noise in ECG signals, which includes two-stage moving-average filter, an infinite impulse response comb filter, an additive white noise generator to test the system’s performance in terms of signal-to-noise ratio,⁴⁴ a low-cost online acquisition of ECG signal using MATLAB^TM and LabVIEW^TM and time-plane feature extraction from digitized ECG samples that uses a statistical approach,⁴⁵ a mobile-based physiological parameter detection and analysis algorithm⁴⁶ ARTiiFACT, a tool for collecting real-time ECG data from integrated sensors and mobile platform to directly collect and analyze the data,⁴⁷ ECG signal processing and digital filtering on 8-bit microcontroller,⁴⁸ and a mean shift-based self-adaptive model.⁴⁹

Personalized and predictive medicine can greatly benefit from data integration and its machine learning model (big data analytics).³⁹ Today, most health systems use a combination of rules-based approaches, as well as manual methods, to best interpret medical data. Big data analysis seems to be a solution for rapidly increasing medical data resulting from the increased use of electronic medical devices and storing of digital data. However, big data analysis is at an early stage and needs more time to achieve clinical acceptance.³⁹

Data processing can be broadly classified into two categories. First, data analysis and processing methods implemented on a smartphone in real time with dense impact on the devices’ battery life. Mostly, such apps cannot be implemented as continuous monitoring apps due to their large power consumption. Moreover, due to the limited hardware and processing powers of the device, sophisticated data processing and interpretation are limited when compared with high-end personal computers.⁵⁰ Second, collected data are being pushed to cloud-based services for processing, and only alerts are transmitted back (generated by the cloud-based apps) and pushed to various other devices. In such apps, the alert will be delayed depending upon Internet connectivity and cloud-processing capabilities, that is, medical decision support rules set up in the cloud.^51,52

Security and privacy

The privacy and security of healthcare data are of the highest importance, especially when healthcare apps deal with personal health data or store patients’ health records, vitals, or laboratory results. Security issues can be classified into two categories: system security and information security. Ng et al.⁵³ have classified threats and attacks into two major categories—passive and active. Kargl et al.⁵⁴ and Williams⁵⁵ have discussed the mHealth apps security and privacy in detail and highlight the types of privacy attacks as modification of medical data; forging of alarms on medical data; denial of service, location, and activity tracking of users; physical tampering with devices; and jamming attacks.

A number of security and privacy frameworks have been developed, designed, and tested for their reliability in mHealth apps, and 22 free web-based personal health record privacy and security policies have been analyzed by Carrión et al.⁵⁶ These researchers reported that a high level of user’s security occurs with apps such as Google Health, ZeabraHealth, Keas, and Microsoft HealthVault.^38,57–59 Various recent reviews and recommendations on security and privacy of mobile healthcare applications have been published.^60–63

Data transmission and information exchange

Mostly, mHealth apps are developed to be either web based or local smartphone based.⁶⁴ In both cases, they can be connected to another software (service) for transfer of information.⁶⁵ However, the local application usually lacks data integration capabilities with other clinical databases to fetch patient data for processing; they mostly relay on local patient data and are limited to analyze specific localized issues. Local machine-based apps have the advantage of patients’ information security and privacy, but have two critical drawbacks: memory space and limited historical patient data access.⁴ However, fully connected apps have the advantage of analyzing wider patient data from other data repositories in order to predict/interpret decision support. Such apps are usually connected to cloud-based environment for information transmission but do require additional information and communications technology (ICT) infrastructure with cost implications at the initial stage. The cloud-based architecture raises issue with privacy and security of patients’ personal information.³⁸ It is suggested that there should be balance between clinical use and ICT dependence for mHealth apps. For example, if the medical device or hospital Internet connectivity fails, then the entire application is unusable by the clinicians because the data are stored in the cloud due to the smartphone/tablet’s limited space.^4,66

It is recommended that in limited resource settings, it is optimal to use the local smartphone application for the specific healthcare area so that huge ICT-related costs could be saved.⁶⁷ Wilcox et al.⁶⁸ attempted to minimize such barriers using advanced data encryption processes where data are encrypted on the tablet computer before being transmitted to the cloud server and data were only decrypted after being retrieved by the target organization. To address the issue of integration/connectivity, the study⁶⁸ used a local application on the device rather than using the tablet computer as a browser for web-based forms. This reduced workflow issues because of connectivity, but also carried the risk of storing information on the device.⁶⁸ Again, this illustrates the importance of ICT infrastructure being able to store and handle huge amounts of incoming patient data. However, storing information on the hand-held device introduces the risk of losing the device (easier to lose the smartphone device than desktop work station) and one cannot physically steal or lose the cloud.

Clinician and end-user consultation

The design of effective mHealth apps is becoming increasingly important. mHealth apps continue to increase, but with little evidence for their effectiveness being shown in clinical outcomes.⁶⁹ Many current mHealth interventions are based on existing/traditional healthcare models and may not be as effective as those that involve end-users in the design process.⁷⁰ Apps need to be produced with adequate consideration of the needs of their intended users so that they become easy to use and perceived as useful.^69,70 Clinician and patient-centric design thinking is required in the initial phase of app design. One of the common scenario of the basic mHealth app requirement is the reviewing of laboratory results with a patient by showing them data from their EHR using patient apps.⁷¹ Thus, an app may enhance the provider–patient experience rather than detract from the overall interaction. An added benefit from such interactions is the ability to transmit educational materials right from a practitioner’s device to the patient, thus reducing the transfer of paper and increasing the likelihood of it being retained for access by the patient. User-centered design is essential in order to incorporate these perceptions into the end-user product, especially at the earlier stages of the project development.⁷² When considering the user’s needs, the solution designer should consider a number of factors such as task analysis, surveys, interviews, and focus groups to address user acceptability issues.⁷³ Highly sophisticated data analysis techniques will become irrelevant if users do not understand the operation and its user interface.⁷⁴

Discussion

Clinical workflows such as nursing documentation, inpatient communication tools, and patient health records are required to be connected to the wider healthcare delivery ecosystems for efficient clinical outcomes. The smartphone-based CDS apps could be seen as a potential standard/best practice tools that will help clinicians to deliver better and more accurate outcomes. The app design, implementation, and evaluation of such platforms require platform rigorous and systematic workflow methodologies. Zheng et al.⁷⁵ identified that there is a discrepancy across the findings of health information technology (IT) studies in terms of their impact on workflow. As they speculated, the discordance may be due in part to oversimplified workflow modeling practices. The patient-orientated workflow methodology and the available automated tool can assist researchers with collecting data that can greatly help clinicians in decision making.^4,66,74 Ng et al.⁷⁶ recommended five main characteristics of smartphone apps in order for them to be clinically acceptable: (1) information exchange to support such apps, (2) evaluation of apps including testing and user training, (3) careful planning to develop robust and safe application, (4) stakeholder involvement toward decision support tools, and (5) traditional face-to-face interaction should not be reduced or compromised and final decision making should be based on the clinicians’ experience and knowledge and not solely technology-driven. Current smartphone apps can accurately support the time-based actions such as alerts, reminders, notifications, and warnings. These apps can be considered to be a reliable data collector and transmitter tool which supports the structured data collection and storage. However, most of the healthcare apps lack other system integration, have poor execution of CDS, and have low user acceptance and also lack of implementation in the hospital care setting.^8,42,71

It is now widely believed that younger generations have been exposed to technology from an early age and a large percentage of their education has utilized some level of technology exposure. Therefore, they exhibit favorable attitudes toward innovative technology, thus resulting in its rapid adoption.⁷⁷ A study revealed that new technology was initially utilized in hospital care, because it was popular in the workplace among other colleagues. It was not until the device was used for some time in practice that experienced medical professionals recognized its full potential (when compared to younger medical professionals). It is also possible that due to their greater knowledge and experience, they needed these devices less than their younger colleagues. Due to this technological exposure, it may be assumed that less experienced (younger) physicians are more rapidly adopting smartphone technology into hospital care/clinical practice than other more experienced medical professional.^78,79

Conclusion

Three common issues are currently facing the wider mHealth application domain. First, smartphone apps are being tested/evaluated in hospital care settings involving senior clinicians. Second, there is a need for the continuous involvement of medical professional and end-user in the app design. Third, accurate data analysis and interpretation can be provided to the medical professional via smartphone application in a reasonable time frame. Existing studies have emphasized the smartphone’s efficiency as a communication and educational tool, a reference source and a decision resource for both patients and healthcare providers.^7,27 Furthermore, recent survey results have demonstrated a positive patient perception of physicians who use smartphone apps in the clinical setting regardless of patient age, race, gender, or income.^74,80

This review also provides an overview of the literature on a broad range of smartphone healthcare apps in hospital care settings. Most of the systems described are either in their development stage or simulation stage but not actually implemented in the hospital care (except systems conducted clinical trials). Further focused research is required in such apps with respect to their clinical implementation, end-user acceptability, evaluation by medical professionals, and security and privacy.

However, the complexity of CDS computation requires a significant amount of processing power during data analysis and executing the decision support algorithms/models. Such models do not permit direct utilization of ubiquitous devices supporting healthcare services due to their limitations. Therefore, instead of complex data processing, either simplified algorithms are suggested to apply on the device or only alerts/notifications should be pushed on the device.

We have identified two core “areas of concerns” related to smartphone computer technology. First, clinicians and patients are the underused resources in smartphone apps design and development. Early collaboration between developers, clinicians, and the target users is critical if the successful healthcare apps are successfully implemented in the hospital care setting. Second, the appropriate use/representation of data including data analysis, interpretation, translation, integration, and processing should be transparent and presented to the medical professional in a simple and easy format. Due to the “big data” coming from multiple eHealth sources, it is now a critical task to represent the raw data in a way that is as meaningful/useful as possible to the clinician. In this way, decision support can be enabled efficiently and in real-time. Currently, most systems lack clinical or secondary care implementation. Very few apps are available today which incorporate and address critical aspects such as design, development, implementation, and user/clinicians collaboration.

Footnotes

Declaration of conflicting interest

The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Funding

The author(s) received no financial support for the research, authorship, and/or publication of this article.

References

Ebad

Ubiquitous computing: a brief review of impacts and issues. Scal Comput Pract Exp 2014; 2(3): 59–68.

Baig

GholamHosseini

Connolly

MJ.

Mobile healthcare applications: system design review, critical issues and challenges. Australas Phys Eng Sci Med 2015; 38: 23–38.

Baig

Gholamhosseini

Smart health monitoring systems: an overview of design and modeling. J Med Syst 2013; 37(2): 9898.

Akhlaq

McKinstry

Muhammad

, et al. Barriers and facilitators to health information exchange in low- and middle-income country settings: a systematic review. Health Policy Plann 2016; 31: 1310–1325.

Taticchi

Garengo

Nudurupati

, et al. A review of decision-support tools and performance measurement and sustainable supply chain management. Int J Prod Res 2015; 53(21): 6473–6494.

Baig

Gholamhosseini

Connolly

MJ.

A comprehensive survey of wearable and wireless ECG monitoring systems for older adults. Med Biol Eng Comput 2013; 51(5): 485–495.

McColl

Rideout

Parmar

, et al. Peer support intervention through mobile application: an integrative literature review and future directions. Can Psychol 2014; 55(4): 250–257.

Silva

Rodrigues

de la Torre Díez

, et al. Mobile-health: a review of current state in 2015. J Biomed Inform 2015; 56: 265–272.

Volk

Llewellyn-Thomas

Stacey

, et al. Ten years of the international patient decision aid standards collaboration: evolution of the core dimensions for assessing the quality of patient decision aids. BMC Med Inform Decis 2013; 13(Suppl. 2): S1.

10.

Malvey

Slovensky

DJ.

mHealth products, markets, and trends. In: mHealth: transforming healthcare. Boston, MA: Springer, 2014, pp. 65–94.

11.

Shin

. Ubiquitous healthcare platform for chronic patients. In: 2016 international conference on platform technology and service (PlatCon), Jeju, South Korea, 15–17 February 2016. New York: IEEE.

12.

Adamson

The persistent challenge of health informatics. Inform Commun Soc 2016; 19(4): 551–558.

13.

Nguyen

Silva

JN.

Use of smartphone technology in cardiology. Trends Cardiovas Med 2016; 26(4): 376–386.

14.

Natarajan

Prasath

Kokila

Smart health care system using Internet of things. J Netw Commun Emerg Technol 2016; 6(3): 37–42.

15.

Herterich

Peters

Neff

, et al. Mobile work support for field service: a literature review and directions for future research. In: Wirtschaftsinformatik proceedings, Osnabrück, 4–5 March 2015.

16.

Friesen

Hamel

McLeod

RD.

A mHealth application for chronic wound care: findings of a user trial. Int J Environ Res Public Health 2013; 10(11): 6199–6214.

17.

Black

Baharestani

Cuddigan

, et al. National Pressure Ulcer Advisory Panel’s updated pressure ulcer staging system. Adv Skin Wound Care 2007; 20(5): 269–274.

18.

Bergstrom

Braden

Laguzza

, et al. The Braden scale for predicting pressure sore risk. Nurs Res 1987; 36(4): 205–210.

19.

Harris

Bates-Jensen

Parslow

, et al. Bates-Jensen wound assessment tool: pictorial guide validation project. J Wound Ostomy Continence Nurs 2010; 37(3): 253–259.

20.

Steinhubl

Muse

Topol

EJ.

The emerging field of mobile health. Sci Transl Med 2015; 7(283): 283rv3.

21.

Lupşe

O-S

Vida

Stoicu-Tivadar

, et al. Cloud computing and interoperability in healthcare information systems. In: The first international conference on intelligent systems and applications, Chamonix, 29 April–4 May 2012.

22.

Pandria

Spachos

Bamidis

, et al. The future of mobile health ADHD applications. In: International conference on interactive mobile communication technologies and learning (IMCL), Thessaloniki, 19–20 November 2015. New York: IEEE.

23.

Adibi

Mobile health: a technology road map. Berlin: Springer, 2015.

24.

Ventola

CL.

Mobile devices and apps for health care professionals: uses and benefits. Pharm Ther 2014; 39(5): 356–364.

25.

Market Research. mHealth apps and solutions market by connected devices: global trends and forecast to 2018. Rockville, MD: Market Research, 2013.

26.

Dexheimer

Borycki

EM.

Use of mobile devices in the emergency department: a scoping review. Health Informatics J 2014; 21: 306–315.

27.

Sclafani

Tirrell

Franko

OI.

Mobile tablet use among academic physicians and trainees. J Med Syst 2013; 37(1): 9903.

28.

Doty

Kellihan

Jung

, et al. The wearable multimodal monitoring system: a platform to study falls and near-falls in the real-world. In: International conference on human aspects of IT for the aged population, Los Angeles, CA, 2–7 August 2015. Cham: Springer.

29.

Haescher

Matthies

Trimpop

, et al. A study on measuring heart- and respiration-rate via wrist-worn accelerometer-based seismocardiography (SCG) in comparison to commonly applied technologies. In: Proceedings of the 2nd international workshop on sensor-based activity recognition and interaction, Rostock, 25–26 June 2015. New York: ACM.

30.

Horta

Lopes

Rodrigues

. Ubiquitous mHealth approach for biofeedback monitoring with falls detection techniques and falls prevention methodologies. In: Adibi

(ed.) Mobile health: a technology road map. Cham: Springer, 2015, pp. 43–75.

31.

Starostenko

Alarcon-Aquino

Rodriguez-Asomoza

, et al. mHealth and remote vital sign monitoring: trends and applications for ECG analysis on cell phones. In: Adibi

(ed.) Mobile health: a technology road map. Cham: Springer, 2015, pp. 221–243.

32.

Ghassemi

Celi

Stone

DJ.

State of the art review: the data revolution in critical care. Crit Care 2015; 19(1): 118.

33.

Tsai

C-W

Chiang

M-C

Ksentini

, et al. Metaheuristic algorithms for healthcare: open issues and challenges. Comput Electr Eng 2016; 53: 421–434.

34.

Umair

Muneer

Zahoor

, et al. Mobile cloud computing future trends and opportunities. In: Kannan

Rasool

Jin

, et al. (eds) Managing and processing big data in cloud computing. Hershey, PA: IGI Global, 2016, pp. 105–120.

35.

Ullah

Higgins

Braem

, et al. A comprehensive survey of wireless body area networks. J Med Syst 2012; 36(3): 1065–1094.

36.

Pandey

Voorsluys

Niu

, et al. An autonomic cloud environment for hosting ECG data analysis services. Future Gener Comp Sy 2012; 28(1): 147–154.

37.

Baig

GholamHosseini

Linden

, et al. Review of vital signs monitoring systems: patient’s acceptability, issues and challenges. Neurosci Biomed Eng 2014; 2(1): 2–13.

38.

Al Ameen

Liu

Kwak

. Security and privacy issues in wireless sensor networks for healthcare applications. J Med Syst 2012; 36(1): 93–101.

39.

Murdoch

Detsky

AS.

The inevitable application of big data to health care. JAMA 2013; 309(13): 1351–1352.

40.

Groves

Kayyali

Knott

, et al. The big data revolution in healthcare: accelerating value and innovation. New York: McKinsey Global Institute, 2013.

41.

Brown

Adams

AA.

The ethical challenges of ubiquitous healthcare. Int Rev Inform Ethics 2007; 8(12): 53–60.

42.

Mosa

ASM

Yoo

Sheets

A systematic review of healthcare applications for smartphones. BMC Med Inform Decis Mak 2012; 12(1): 67.

43.

McQueen

Cress

Tothy

. Using a tablet computer during pediatric procedures: a case series and review of the “apps.” Pediatr Emerg Care 2012; 28(7): 712–714.

44.

Rangayyan

Zhou

, et al. Filtering electrocardiographic signals using an unbiased and normalized adaptive noise reduction system. Med Eng Phys 2009; 31(1): 17–26.

45.

Chatterjee

Gupta

Mitra

A statistical approach for determination of time plane features from digitized ECG. Comput Biol Med 2011; 41(5): 278–284.

46.

Merzougui

Feham

Sedjelmaci

Design and implementation of an algorithm for cardiac pathologies detection on mobile phone. Int J Wirel Inform Netw 2011; 18(1): 11–23.

47.

Kaufmann

Sütterlin

Schulz

, et al. ARTiiFACT: a tool for heart rate artifact processing and heart rate variability analysis. Behav Res Methods 2011; 43(4): 1161–1170.

48.

Shin

Cha

Yoon

ECG/PPG integer signal processing for a ubiquitous health monitoring system. J Med Syst 2010; 34(5): 891–898.

49.

Yan

Liu

, et al. Self-adaptive model-based ECG denoising using features extracted by mean shift algorithm. Biomed Signal Proces 2010; 5(2): 103–113.

50.

Mayer-Schönberger

Cukier

Big data: A revolution that will transform how we live, work, and think. New York: Houghton Mifflin Harcourt, 2013.

51.

Raghupathi

Big data analytics in healthcare: promise and potential. Health Inform Sci Syst 2014; 2(1): 3.

52.

Kayyali

Knott

Van Kuiken

The big-data revolution in US health care: Accelerating value and innovation. Mc Kinsey & Company April 2013; 2(8): 1–3.

53.

Sim

Tan

Security issues of wireless sensor networks in healthcare applications. BT Technol J 2006; 24(2): 138–144.

54.

Kargl

Lawrence

Fischer

, et al. Security, privacy and legal issues in pervasive eHealth monitoring systems. In: 7th international conference on mobile business (ICMB ‘08), Barcelona, 7–8 July 2008. New York: IEEE.

55.

Williams

. Social networking applications in health care: threats to the privacy and security of health information. In: Proceedings of the 2010 ICSE workshop on software engineering in health care, Cape Town, South Africa, 3–4 May 2010, pp. 39–49. New York: ACM.

56.

Carrión

Fernández-Alemán

Toval

Usable privacy and security in personal health records. In: Campos

Graham

Jorge

, et al. (eds) Human-computer interaction—INTERACT 2011 (Lecture Notes in Computer Science 6949). Berlin/Heidelberg: Springer, 2011, pp. 36–43.

57.

Ming

Wenjing

Kui

Data security and privacy in wireless body area networks. Wirel Commun 2010; 17(1): 51–58.

58.

Kotz

Avancha

Baxi

. A privacy framework for mobile health and home-care systems. In: First ACM workshop on security and privacy in medical and home-care systems; Chicago, IL, 13 November 2009, pp. 1–12. New York: ACM.

59.

Xiaodong

Rongxing

Xuemin

, et al. SAGE: a strong privacy-preserving scheme against global eavesdropping for eHealth systems. IEEE J Sel Area Comm 2009; 27(4): 365–378.

60.

Kumar

Nilsen

Abernethy

, et al. Mobile health technology evaluation: the mHealth evidence workshop. Am J Prev Med 2013; 45(2): 228–236.

61.

Martínez-Pérez

Torre-Díez

López-Coronado

Privacy and security in mobile health apps: a review and recommendations. J Med Syst 2015; 39(1): 181.

62.

Dehling

Gao

Schneider

, et al. Exploring the far side of mobile health: information security and privacy of mobile health apps on iOS and Android. JMIR Mhealth Uhealth 2015; 3(1): e8.

63.

Powell

Landman

Bates

DW.

In search of a few good apps. JAMA 2014; 311(18): 1851–1852.

64.

Hilton

Christi

Dig

, et al. Refactoring local to cloud data types for mobile apps. In: Proceedings of the 1st international conference on mobile software engineering and systems, Hyderabad, India, 2–3 June 2014. New York: ACM.

65.

Erman

Gerber

, et al. Identifying diverse usage behaviors of smartphone apps. In: 2011 ACM SIGCOMM conference on internet measurement conference, Berlin, 2–4 November 2011. New York: ACM.

66.

Serrano

Riley

, et al. Willingness to exchange health information via mobile devices: findings from a population-based survey. Ann Fam Med 2016; 14(1): 34–40.

67.

Sultan

Making use of cloud computing for healthcare provision: opportunities and challenges. Int J Inform Manage 2014; 34(2): 177–184.

68.

Wilcox

Gallagher

Boden-Albala

, et al. Research data collection methods: from paper to tablet computers. Med Care 2012; 50: S68–S73.

69.

Schnall

Rojas

Bakken

, et al. A user-centered model for designing consumer mobile health (mHealth) applications (apps). J Biomed Inform 2016; 60: 243–251.

70.

Briz-Ponce

García-Peñalvo

FJ.

An empirical assessment of a technology acceptance model for apps in medical education. J Med Syst 2015; 39(11): 176.

71.

Zapata

Fernández-Alemán

Idri

, et al. Empirical studies on usability of mHealth apps: a systematic literature review. J Med Syst 2015; 39(2): 1.

72.

Chawla

Davis

DA.

Bringing big data to personalized healthcare: a patient-centered framework. J Gen Intern Med 2013; 28(3): 660–665.

73.

McCurdie

Taneva

Casselman

, et al. mHealth consumer apps: the case for user-centered design. Biomed Instrum Technol 2012; 46(Suppl. 2): 49–56.

74.

Schobel

Pryss

Schickler

, et al. End-user programming of mobile services: empowering domain experts to implement mobile data collection applications. In: IEEE international conference on mobile services, San Francisco, CA, 27 June–2 July 2016.

75.

Zheng

Haftel

Hirschl

, et al. Quantifying the impact of health IT implementations on clinical workflow: a new methodological perspective. J Am Med Inform Assoc 2010; 17(4): 454–461.

76.

Lee

, et al. Health innovations in patient decision support: bridging the gaps and challenges. Australas Med J 2013; 6(2): 95–99.

77.

Sultan

Reflective thoughts on the potential and challenges of wearable technology for healthcare provision and medical education. Int J Inform Manage 2015; 35(5): 521–526.

78.

Kuhn

Crowley

Hoffman

, et al. Clinician characteristics and perceptions related to use of the PE (prolonged exposure) coach mobile app. Prof Psychol Res Pract 2015; 46(6): 437–443.

79.

Lee

Sullivan

Schneiders

, et al. Smartphone and tablet apps for concussion road warriors (team clinicians): a systematic review for practical users. Br J Sports Med 2015; 49(8): 499–505.

80.

Dias

Ribeiro

Furtado

. An overview about the use of healthcare applications on mobile devices. In: Cruz-Cunha

Miranda

Martinho

, et al. (eds) Encyclopedia of e-Health and telemedicine. Hershey, PA: IGI Global, 2016, pp. 285–298.

Clinical decision support systems in hospital care using ubiquitous devices: Current issues and challenges

Abstract

Keywords

Introduction

Materials and methods

Smartphone-based CDS applications

Structured information for mHealth applications

Digital transformation for CDS applications

Data analysis using smartphone applications

Current issues and challenges of smartphone applications in hospital care settings

Data processing and “big” data analysis

Security and privacy

Data transmission and information exchange

Clinician and end-user consultation

Discussion

Conclusion

Footnotes

Declaration of conflicting interest

Funding

References