IT in healthcare

This paper scrutinises how AI and robotic technologies are transforming the relationships between people and machines in new affective, embodied and relational ways. Through investigating what it means to exist as human ‘in relation’ to AI across health and care contexts, we aim to make three main contributions. (1) We start by highlighting the complexities of philosophical issues surrounding the concepts of “artificial intelligence” and “ethical machines.” (2) We outline some potential challenges and opportunities that the creation of such technologies may bring in the health and care settings. We focus on AI applications that interface with health and care via examples where AI is explicitly designed as an ‘augmenting’ technology that can overcome human bodily and cognitive as well as socio-economic constraints. We focus on three dimensions of ‘intelligence’ - physical, interpretive, and emotional - using the examples of robotic surgery, digital pathology, and robot caregivers, respectively. Through investigating these areas, we interrogate the social context and implications of human-technology interaction in the interrelational sphere of care practice. (3) We argue, in conclusion, that there is a need for an interdisciplinary mode of theorising ‘intelligence’ as relational and affective in ways that can accommodate the fragmentation of both conceptual and material boundaries between human and AI, and human and machine. Our aim in investigating these sociological, philosophical and ethical questions is primarily to explore the relationship between affect, relationality and ‘intelligence,’ the intersection and integration of ‘human’ and ‘artificial’ intelligence, through an examination of how AI is used across different dimensions of intelligence. This allows us to scrutinise how ‘intelligence’ is ultimately conveyed, understood and (technologically or algorithmically) configured in practice through emerging relationships that go beyond the conceptual divisions between humans and machines, and humans vis-à-vis artificial intelligence-based technologies.

The US government recommends that hospitals adopt Computerized Provider Order Entry (CPOE) systems to improve the quality problems that plague US hospitals. However, CPOE studies show mixed results. We hypothesize that CPOE effectiveness depends on the prevalence of patient safety culture within a hospital. Using organizational information processing theory, we describe how patient safety culture and CPOE enable healthcare organizations to better process information. Specifically, we posit that CPOE complements some aspects of patient safety culture and substitutes for others. Using ridge regression, we empirically test this proposition using data from 268 hospitals and multiple data sources. Results show that while CPOE complements the patient safety dimensions of handoffs and transitions, feedback and communication about error, and organizational learning, CPOE substitutes for the dimension of management support for safety, in the context of our dependent variable. As organizations work to implement new systems, this research can help decision-makers understand how culture impacts such initiatives and account for culture when anticipating effects.

Fog computing (FC) is an evolving computing technology that operates in a distributed environment. FC aims to bring cloud computing features close to edge devices. The approach is
expected to fulfill the minimum latency requirement for healthcare Internet-of-Things (IoT)
devices. Healthcare IoT devices generate various volumes of healthcare data. This large
volume of data results in high data traffic that causes network congestion and high latency.
An increase in round-trip time delay owing to large data transmission and large hop counts
between IoTs and cloud servers render healthcare data meaningless and inadequate for
end-users. Time-sensitive healthcare applications require real-time data. Traditional cloud
servers cannot fulfill the minimum latency demands of healthcare IoT devices and endusers. Therefore, communication latency, computation latency, and network latency must
be reduced for IoT data transmission. FC affords the storage, processing, and analysis of
data from cloud computing to a network edge to reduce high latency. A novel solution for the
abovementioned problem is proposed herein. It includes an analytical model and a hybrid
fuzzy-based reinforcement learning algorithm in an FC environment. The aim is to reduce
high latency among healthcare IoTs, end-users, and cloud servers. The proposed intelligent
FC analytical model and algorithm use a fuzzy inference system combined with reinforcement learning and neural network evolution strategies for data packet allocation and selection in an IoT–FC environment. The approach is tested on simulators iFogSim (Net-Beans)
and Spyder (Python). The obtained results indicated the better performance of the proposed
approach compared with existing methods

Vital signs monitoring is a customarily repetitive, tedious part of patient care that nonetheless requires constant measurements and documentations to avert significant adverse consequences. Routinely performed by nurses, measurements of vital signs are recorded at regular intervals for safeguarding patient safety yet some evidence concerning the frequency of noncompliance in vital sign collection as well as the inaccuracy of vital sign measurements is still at large. This paper covered the development of a patient monitoring device using hardware modules such as pulse rate sensor, sphygmomanometer, and body temperature sensor that communicates through wireless technology protocol based on IEEE 802.15.4 standard for synchronous measurements of multiple vital signs such as body temperature, pulse rate, and blood pressure. Physiological data accuracy based from the Modified Early Warning Score was measured by Bland-Altman and Pearson correlation analysis, and user acceptability was inspected using IoT technology trust model with the aid of health professionals and patients from hospitals and diagnostic centers. Vital sign measurements by VITAL APP and health professionals correlated well, and the device was accepted as an important tool in patient monitoring.

This paper reports the outcomes of a study on an integrated situational alignment framework for picture archiving and communication systems (PACS) labeled as PISA. Following the design research cycle, complementary validation methods and pilot cases were used to assess the proposed framework and its operationalized survey. In this paper, the authors outline (a) the process of the framework' development, (b) the validation process with its underlying iterative steps, (c) the outcomes of pilot cases, and (d) improvement opportunities to refine and further validate the PISA framework. Results of this study support empirical application of the framework to hospital enterprises in order to gain insights into their PACS maturity and alignment. We argue that the framework can be applied as a valuable tool for assessments, monitoring and benchmarking purposes and strategic PACS planning.

Innovation in information and communication technology has a great potential to create large impact on modern healthcare. However, for the new technologies to be adopted, the innovations have to be meaningful and timely, taking into account user needs and addressing societal and ethical concerns. In this paper, we focus on ICT innovations related to home healthcare domain, in which patient safety and security, but also trust and privacy are of utmost im-portance. To ensure the adoption of new healthcare services, the new innovative technologies need to be complemented with new methods that can help patients to establish trust in healthcare service providers in terms of privacy, reliability, integrity of the data chain and techniques that help service providers to assess the reliability of information and data contributed by patients. This paper sketches various lines of research for the development of trusted healthcare ser-vices namely, patient compliance, reliability of information in healthcare, and user-friendly access control.

Healthcare service is one of the focus areas in supporting the existence of smart city. Nowadays, many procedures are done paperless and fully in digital. Medical scanning is also stored in digital modalities format and transmitted through a hospital management system. An authentication system is needed during the transmission, thus the need of watermarking. Some interesting research directions in watermarking include the embedding pattern of watermark data in the early process of watermarking. The objective of this research is to investigate the best pattern to determine the bit locations for watermark embedding for copyright protection. This paper applies four types of embedding patterns on medical images, which the quality of watermarked images would depend on how the mapping pattern is. It compares the difference of having a straight forward pattern mapping as a raster pattern and a unique pattern mapping like spiral, Hilbert, and Peano patterns. After mapping, all would have the same stages of a watermarking scheme which are embedding, detection and recovery stage. The comparison factors include the peak-signal-noise-ratio, mean-squared-error values of embedded images, and the computational time. From the result, the significant difference is the computational time; the taken time by the unique pattern is significantly longer than raster. When it comes to handling superabundant data, it is very crucial to produce a user-friendly system. However, as a whole, the results from Peano pattern embedding scheme shows it has a unique pattern which hard to be tracked, yet, its computational time to watermark is acceptable.

Objective: To evaluate the feasibility of a phase 3
randomised controlled trial (RCT) of a website (Living
Well with Asthma) to support self-management.
Design and setting: Phase 2, parallel group, RCT,
participants recruited from 20 general practices across
Glasgow, UK. Randomisation through automated voice
response, after baseline data collection, to website
access for minimum 12 weeks or usual care.
Participants: Adults (age≥16 years) with physician
diagnosed, symptomatic asthma (Asthma Control
Questionnaire (ACQ) score ≥1). People with unstable
asthma or other lung disease were excluded.
Intervention: ‘Living Well with Asthma’ is a desktop/
laptop compatible interactive website designed with
input from asthma/ behaviour change specialists, and
adults with asthma. It aims to support optimal
medication management, promote use of action plans,
encourage attendance at asthma reviews and increase
physical activity.
Outcome measures: Primary outcomes were
recruitment/retention, website use, ACQ and miniAsthma
Quality of Life Questionnaire (AQLQ).
Secondary outcomes included patient activation,
prescribing, adherence, spirometry, lung inflammation
and health service contacts after 12 weeks. Blinding
postrandomisation was not possible.
Results: Recruitment target met. 51 participants
randomised (25 intervention group). Age range
16–78 years; 75% female; 28% from most deprived
quintile. 45/51 (88%; 20 intervention group) followed
up. 19 (76% of the intervention group) used the
website, for a mean of 18 min (range 0–49). 17 went
beyond the 2 ‘core’ modules. Median number of logins
was 1 (IQR 1–2, range 0–7). No significant difference
in the prespecified primary efficacy measures of ACQ
scores (−0.36; 95% CI −0.96 to 0.23; p=0.225), and
mini-AQLQ scores (0.38; −0.13 to 0.89; p=0.136). No
adverse events.
Conclusions: Recruitment and retention confirmed
feasibility; trends to improved outcomes suggest use of
Living Well with Asthma may improve self-management
in adults with asthma and merits further development
followed by investigation in a phase 3 trial.
Trial registration number: ISRCTN78556552;
Results.

Healthcare sector is information critical industry that deals with human lives. Transforming from traditional paper-based to Electronic Health Records (EHRs) was not efficient enough since EHRs require resources, integration, maintenance and high cost implementation. Cloud computing paradigm offers flexible, cost effective, collaborative, multi-tenant infrastructure which assists in transforming electronic healthcare to smart healthcare that consists on the use of latest technologies such as smart mobiles, smart cards, robots, sensors and Tele-health systems via internet on pay-per-use basis for best medical practices. Cloud computing reduces the cost of EHRs in terms of ownership and IT maintenance, also it offers sharing, integration and management of EHRs as well as tracking patients and diseases more efficiently and effectively. This review paper represents the significance and opportunities for implementing cloud computing in healthcare sector.

This article reports the results of a case study of the consequences of mobile device use for the work practices of operating room nurses. The study identifies different patterns of mobile technology use by operating room nurses, including both work-related and non-work-related use. These patterns have multiple consequences for nurses, such as improvements in information access, e-learning and work-related communication, as well as a perceived increase in distractions from the collaborative work. We conceptualize these consequences in terms of three level effects and explain how we find both positive and negative consequences on the third level. On the positive side, improvements were found in how nurses spent their unoccupied time during the stable parts of operations, contributing to their well-being and job satisfaction. A negative consequence was the perceived increase in distraction from the collaborative operating room work practices.

This study presents compelling social indicators of such magnitude that they cannot be ignored. Medical records of ~50% US population have been compromised. The statistical evidence shows that data breaches of electronic health records have taken place at an unprecedented scale. Currently, the number of individuals affected, as regulations of Health Insurance Portability and Accountability Act refers to us, has surpassed the half of the US population (some data is breached several times lowering the number of victims but increasing the possibility of being sold quickly). The data breaches are recorded and posted by Department of Health and Human Services.

Cardiovascular diseases are the world’s leading cause of death, with a reported 17.9 million deaths per year [1]. Most cardiovascular diseases are detected by heart rate variations. For this proposal, we have developed a cloud-IoT system based on agents for remote heart rate monitoring, which simplifies the tracking and monitoring of patients with cardiovascular disease in any place. The proposed system can collect, retrieve, store, and analyze the heart rate of the patient. It can also take a quick and smart decision in an emergency case. It can be used not only by the hospital but also by any health care provider.

OBJECTIVE. The purpose of this study is to validate an electronic learning, or e-learning, concept featuring gami cation elements, rapid case reading, and instant feedback. SUBJECTS AND METHODS. An e-learning concept was devised that offered game levels for the purpose of providing training in the detection of pneumothorax in 195 cases, with questions read in rapid succession and instant feedback provided for each case. The user's task was to locate the pneumothorax on chest radiographs and indicate its presence by clicking a mouse. The game level design included an entry test consisting of 15 cases, training levels with increasing dif culty that involved 150 cases, and a nal test that including 30 cases (the 15 cases from the entry test plus 15 new cases). A total of 126 candidates were invited via e-mail to participate and were asked to complete a survey before and after playing the game, which is known as RapRad. The level of diagnostic con dence and the error rate before and after playing the game were compared using a Wilcoxon signed rank test. RESULTS. Fifty-nine of 126 participants (47%) responded to the rst survey and nished the game. Of these 59 participants, 29 (49%) responded to the second survey after completing the game. Diagnostic con dence in pneumothorax detection improved signi cantly, from a mean (± SD) score of 4.3 ± 2.1 on the entry test to a nal score of 7.3 ± 2.1 (p < 0.01) after playing RapRad, with the score measured on a 10-point scale, with 10 denoting the highest possible score. Of the participants, 93% indicated that they would use the game for learning purposes again, and 87% indicated that they had fun using RapRad (7% had a neutral response and 6% had a negative response). The error rate (i.e., the number of failed attempts to answer a question correctly) signi cantly decreased from 39% for the entry test to 22% for the nal test (p < 0.01). CONCLUSION. Our e-learning concept is capable of improving diagnostic con dence, reducing error rates in training pneumothorax detection, and offering fun in interaction with the platform.

This study examined how one US hospital implemented a mobile communication app to improve workplace communication. The hospital did not provide the technology, instead they asked their workers to use their own personal mobiles at work, through a permissive bring your own device to work (BYOD) policy. Using boundary theory, we conducted a constant-comparative analysis to examine the layers of boundary management issues. At the organizational level, the key issues were policy legacy, communicating the policy, control, dead zones, and mobile costs. At the group level, different hospital units created their own formal and informal policies. At the individual level, themes included personal mobile device use, job role expectations, and decision-making autonomy. The discussion presents examples of how healthcare workers enacted segregator and integrator boundaries. Our findings explain why it is not easy to tell hospital employees, " Go ahead and use your mobiles for patient care, " and have them embrace this practice.

Pervasive intelligent environments, such as digital homes, offer huge potentials for eHealth services. However, there is a question as to how best to manage (i.e. configure and program) these systems. The majority of solutions to-date rely exclusively on either end users or autonomous agents to manage the environment, which may not be suitable for all users and in certain situations, especially in eHealth applications where uses may have very specific requirements that can change considerably over time. In this work-in-progress paper we argue that human-agent teamwork is vital for the adoption of future pervasive computing systems into our everyday lives; we discuss these issues, exposing the problem of exclusive management and we explore a solution, presenting our novel architecture for an adjustable autonomy agent that enables human-agent based teamwork. This work contributes to the PAL project: a collaborative research effort between University of Essex, BT, University of Cambridge and Ericsson.