A Rapid Review on Application Scenarios for Artificial Intelligence in Nursing Care (Preprint)

2020 ◽  
Author(s):  
Kathrin Seibert ◽  
Dominik Domhoff ◽  
Dominik Bruch ◽  
Matthias Schulte-Althoff ◽  
Daniel Fürstenau ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Technology Acceptance ◽  
Nursing Care ◽  
Technology Use ◽  
Data Privacy ◽  
Clinical Decision Making ◽  
Machine Learning Algorithms ◽  
Rapid Review ◽  
Social Implications ◽  
Original Research

BACKGROUND Artificial intelligence (AI) holds the promise to support nurses’ clinical decision making in complex care situations or to conduct tasks that are remote from direct patient interaction such as documentation processes. There has been an increase in research and development of AI applications for nursing care, but a persistent lack of an extensive overview covering the evidence-base for promising application scenarios. OBJECTIVE The paper synthesizes literature on application scenarios for AI in nursing care settings, as well as highlighting adjacent aspects in the ethical, legal and social discourses surrounding the application of AI in nursing care. METHODS Following a rapid review design, databases PubMed, CINAHL, ACM Digital Library, IEEE Xplore, DBLP, and AIS Library, as well as the libraries of leading conferences were searched in June 2020. Publications of quantitative and qualitative original research, systematic reviews, or discussion papers and essays on ethical, legal, and social implications were eligible for inclusion. Based on predetermined selection criteria, eligible studies were analyzed. RESULTS Titles and abstracts of 6,818 publications and 699 fulltexts were screened and 285 publications have been included. Hospitals were the most prominent setting, followed by independent living-at-home, whereas less application scenarios for nursing homes or homecare were identified. Most studies employed machine learning algorithms while expert or hybrid systems were entailed in less than every tenth publication. Application context focused on image and signal processing with tracking, monitoring or classification of activity and health followed by care coordination and communication as well as fall detection was the main purpose of AI applications. Few studies reported effects for clinical or organizational outcomes of AI applications, lacking particularly in data gathered outside of laboratory conditions. Aside from technological requirements, reporting on requirements captures more overarching topics such as data privacy, safety or technology acceptance. Ethical, legal and social implications reflected the discourse on technology use in health care, but have gone mostly undiscussed in detail. CONCLUSIONS The results highlight potential for the application of AI systems in different care settings. With regard to the lack of findings on effectiveness and application of AI systems in real-world scenarios, future research should reflect on a more nursing care specific perspective on objectives, outcomes and benefits. We find an advancement in the technological-societal discourse, surrounding the ethical and legal implications of AI applications in nursing care, to be a practical and needed next step for similar research groups. Further, we outline the need for a greater participation among stakeholders. CLINICALTRIAL not applicable

scholarly journals Artificial Intelligence in Health in 2018: New Opportunities, Challenges, and Practical Implications

2019 ◽  
Vol 28 (01) ◽  
pp. 052-054
Author(s):  
Gretchen Jackson ◽  
Jianying Hu ◽  
Keyword(s):  
Artificial Intelligence ◽  
Domain Knowledge ◽  
English Language ◽  
Machine Learning Algorithms ◽  
Original Research ◽  
Domain Experts ◽  
Ovid Medline ◽  
Significant Research ◽  
Health Applications

Objective: To summarize significant research contributions to the field of artificial intelligence (AI) in health in 2018. Methods: Ovid MEDLINE® and Web of Science® databases were searched to identify original research articles that were published in the English language during 2018 and presented advances in the science of AI applied in health. Queries employed Medical Subject Heading (MeSH®) terms and keywords representing AI methodologies and limited results to health applications. Section editors selected 15 best paper candidates that underwent peer review by internationally renowned domain experts. Final best papers were selected by the editorial board of the 2018 International Medical Informatics Association (IMIA) Yearbook. Results: Database searches returned 1,480 unique publications. Best papers employed innovative AI techniques that incorporated domain knowledge or explored approaches to support distributed or federated learning. All top-ranked papers incorporated novel approaches to advance the science of AI in health and included rigorous evaluations of their methodologies. Conclusions: Performance of state-of-the-art AI machine learning algorithms can be enhanced by approaches that employ a multidisciplinary biomedical informatics pipeline to incorporate domain knowledge and can overcome challenges such as sparse, missing, or inconsistent data. Innovative training heuristics and encryption techniques may support distributed learning with preservation of privacy.

scholarly journals Predicting infection and sepsis; what predictors have been used to train machine learning algorithms? A systematic review

2021 ◽  
Vol 29 (Supplement_1) ◽  
pp. i18-i18
Author(s):  
N Hassan ◽  
R Slight ◽  
D Weiand ◽  
A Vellinga ◽  
G Morgan ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Systematic Review ◽  
Decision Making ◽  
Quality Assessment ◽  
Clinical Decision Making ◽  
Data Extraction ◽  
Learning Algorithms ◽  
Clinical Decision ◽  
Machine Learning Algorithms

Abstract Introduction Sepsis is a life-threatening condition that is associated with increased mortality. Artificial intelligence tools can inform clinical decision making by flagging patients who may be at risk of developing infection and subsequent sepsis and assist clinicians with their care management. Aim To identify the optimal set of predictors used to train machine learning algorithms to predict the likelihood of an infection and subsequent sepsis and inform clinical decision making. Methods This systematic review was registered in PROSPERO database (CRD42020158685). We searched 3 large databases: Medline, Cumulative Index of Nursing and Allied Health Literature, and Embase, using appropriate search terms. We included quantitative primary research studies that focused on sepsis prediction associated with bacterial infection in adult population (>18 years) in all care settings, which included data on predictors to develop machine learning algorithms. The timeframe of the search was 1st January 2000 till the 25th November 2019. Data extraction was performed using a data extraction sheet, and a narrative synthesis of eligible studies was undertaken. Narrative analysis was used to arrange the data into key areas, and compare and contrast between the content of included studies. Quality assessment was performed using Newcastle-Ottawa Quality Assessment scale, which was used to evaluate the quality of non-randomized studies. Bias was not assessed due to the non-randomised nature of the included studies. Results Fifteen articles met our inclusion criteria (Figure 1). We identified 194 predictors that were used to train machine learning algorithms to predict infection and subsequent sepsis, with 13 predictors used on average across all included studies. The most significant predictors included age, gender, smoking, alcohol intake, heart rate, blood pressure, lactate level, cardiovascular disease, endocrine disease, cancer, chronic kidney disease (eGFR<60ml/min), white blood cell count, liver dysfunction, surgical approach (open or minimally invasive), and pre-operative haematocrit < 30%. These predictors were used for the development of all the algorithms in the fifteen articles. All included studies used artificial intelligence techniques to predict the likelihood of sepsis, with average sensitivity 77.5±19.27, and average specificity 69.45±21.25. Conclusion The type of predictors used were found to influence the predictive power and predictive timeframe of the developed machine learning algorithm. Two strengths of our review were that we included studies published since the first definition of sepsis was published in 2001, and identified factors that can improve the predictive ability of algorithms. However, we note that the included studies had some limitations, with three studies not validating the models that they developed, and many tools limited by either their reduced specificity or sensitivity or both. This work has important implications for practice, as predicting the likelihood of sepsis can help inform the management of patients and concentrate finite resources to those patients who are most at risk. Producing a set of predictors can also guide future studies in developing more sensitive and specific algorithms with increased predictive time window to allow for preventive clinical measures.

scholarly journals A Rapid Review on Application Scenarios for Artificial Intelligence in Nursing Care (Preprint)

10.2196/26522 ◽  
2020 ◽  
Author(s):  
Kathrin Seibert ◽  
Dominik Domhoff ◽  
Dominik Bruch ◽  
Matthias Schulte-Althoff ◽  
Daniel Fürstenau ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Nursing Care ◽  
Rapid Review

Robotics in ALS – Acceptance of Enhanced Robotic Assistance Systems in Patients with ALS-Associated Motor Impairment: An Observational Online Study (Preprint)

2020 ◽  
Author(s):  
André Maier ◽  
Cornelia Eicher ◽  
Jörn Kiselev ◽  
Robert Klebbe ◽  
Marius Greuèl ◽  
...  
Keyword(s):  
Gender Difference ◽  
Technology Acceptance ◽  
Nursing Care ◽  
Technology Use ◽  
Rating Scale ◽  
Robotic Arm ◽  
Robotic Assistance ◽  
Younger Patients ◽  
Assistance Systems ◽  
Als Patients

BACKGROUND Amyotrophic Lateral Sclerosis (ALS) is a fatal neurodegenerative disease characterized by a progressive paresis of the extremities, and the loss of manual functioning. Due to the severe functional impairment that the disease entails, ALS requires the provision of comprehensive nursing care and a complex of assistive technology devices. To relieve caregivers and promote patient autonomy, robotic assistance systems are being developed. This trial aims to evaluate the acceptance of technology in general and robotic arm assistance among ALS patients in order to lay the groundwork for the development of a semi-automatic robotic arm which can be controlled by patients via a multimodal user interface, and which will allow users to handle objects and attend to their own bodies. OBJECTIVE Systematic analysis of technology commitment and acceptance of robotic assistance systems from the perspective of physically limited ALS patients. METHODS The investigation was conducted as a study of a prospective cohort. Patients were only included if they had received a medical diagnosis of ALS. Data collection took place via an online questionnaire on the Ambulanzpartner Soziotechnologie (APST) Internet platform. Technological commitment was measured using the Neyer short scale (2012). Furthermore, a multidimensional questionnaire was specially developed to analyze patient acceptance of robotic arm assistance (AMRAA). This questionnaire was accompanied by a video introducing the robot arm. ALS severity was ascertained using the extended ALS Functional rating Scale (ALSFRS-EX). RESULTS 268 ALS patients participated in the survey. The mean age at disease onset was 60 years (SD 10.6 years); 67 % (n=180) were male. The ALS severity score was 42.9 out of 60 on the ALSFRS-extended (SD 11.7 points), with the most relevant restrictions on arms and legs (less than 60 % of normal function). Technological readiness ranked high (top third with 47.2 out 0f 60 points). Younger patients (< 60 years; 50 vs. 46 points) and male (49.5 vs. 44 points) reached significantly higher values. The acceptance of robotic arm assistance (AMRAA) was again significantly higher in younger patients (25.5 vs. 16 points; p < .0001). However, the gender difference within the overall cohort was not significant (female/male: 18 vs. 22; p < .208). The acceptance measure was then correlated to the ALSFRS-EX subscale for arm functioning. The more limited the arm functioning, the higher the acceptance rate of robotic assistance. This relationship proved significant. CONCLUSIONS ALS patients display high technological commitment and feel positive about using technological assistance systems. Younger patients are more open towards technology use in general and robotic assistance in particular. Self-appraisal of technology acceptance, competence, and control conviction was generally higher among men. However, any presumed gender difference vanished when users were asked to rate the anticipated usefulness of the technology, in particular the robotic arm. This is also reflected in users’ increased willingness to use a robotic arm as the functionality of their own arms decreased. Seen from the user perspective, there is currently a need for semi-automatic robotic arms in order to support caregivers and to allow patients to maintain their autonomy. These results form a basis on which robotic prototypes for nursing care can be designed. They also highlight the relevance of robotic assistance systems in promoting patient participation and autonomy in ALS assistive devices schemes.

scholarly journals Exploring healthcare professionals’ understanding and experiences of artificial intelligence technology use in the delivery of healthcare: An integrative review

2019 ◽  
Vol 26 (2) ◽  
pp. 1225-1236 ◽  
Author(s):  
Lucy Shinners ◽  
Christina Aggar ◽  
Sandra Grace ◽  
Stuart Smith
Keyword(s):  
Artificial Intelligence ◽  
Technology Use ◽  
Healthcare Professionals ◽  
Clinical Decision Making ◽  
Healthcare Setting ◽  
Clinical Decision ◽  
Integrative Review ◽  
Ageing Population ◽  
Delivery Of Healthcare ◽  
Delivery Of Care

Background: The integration of artificial intelligence (AI) into our digital healthcare system is seen as a significant strategy to contain Australia’s rising healthcare costs, support clinical decision making, manage chronic disease burden and support our ageing population. With the increasing roll-out of ‘digital hospitals’, electronic medical records, new data capture and analysis technologies, as well as a digitally enabled health consumer, the Australian healthcare workforce is required to become digitally literate to manage the significant changes in the healthcare landscape. To ensure that new innovations such as AI are inclusive of clinicians, an understanding of how the technology will impact the healthcare professions is imperative. Method: In order to explore the complex phenomenon of healthcare professionals’ understanding and experiences of AI use in the delivery of healthcare, an integrative review inclusive of quantitative and qualitative studies was undertaken in June 2018. Results: One study met all inclusion criteria. This study was an observational study which used a questionnaire to measure healthcare professional’s intrinsic motivation in adoption behaviour when using an artificially intelligent medical diagnosis support system (AIMDSS). Discussion: The study found that healthcare professionals were less likely to use AI in the delivery of healthcare if they did not trust the technology or understand how it was used to improve patient outcomes or the delivery of care which is specific to the healthcare setting. The perception that AI would replace them in the healthcare setting was not evident. This may be due to the fact that AI is not yet at the forefront of technology use in healthcare setting. More research is needed to examine the experiences and perceptions of healthcare professionals using AI in the delivery of healthcare.

scholarly journals Explainable Artificial Intelligence (XAI) in Biomedicine: Making AI Decisions Trustworthy for Physicians and Patients

2021 ◽  
Vol 2 (1) ◽  
pp. 1-17
Author(s):  
Jörn Lötsch ◽  
Dario Kringel ◽  
Alfred Ultsch
Keyword(s):  
Artificial Intelligence ◽  
Clinical Decision Making ◽  
Clinical Decision ◽  
Skill Learning ◽  
Machine Learning Algorithms ◽  
Clinical Settings ◽  
Human Beings ◽  
Therapeutic Decisions ◽  
Common Application

The use of artificial intelligence (AI) systems in biomedical and clinical settings can disrupt the traditional doctor–patient relationship, which is based on trust and transparency in medical advice and therapeutic decisions. When the diagnosis or selection of a therapy is no longer made solely by the physician, but to a significant extent by a machine using algorithms, decisions become nontransparent. Skill learning is the most common application of machine learning algorithms in clinical decision making. These are a class of very general algorithms (artificial neural networks, classifiers, etc.), which are tuned based on examples to optimize the classification of new, unseen cases. It is pointless to ask for an explanation for a decision. A detailed understanding of the mathematical details of an AI algorithm may be possible for experts in statistics or computer science. However, when it comes to the fate of human beings, this “developer’s explanation” is not sufficient. The concept of explainable AI (XAI) as a solution to this problem is attracting increasing scientific and regulatory interest. This review focuses on the requirement that XAIs must be able to explain in detail the decisions made by the AI to the experts in the field.

scholarly journals 430 A Review of Artificial Intelligence Solutions for Hepatocellular Carcinoma

2021 ◽  
Vol 108 (Supplement_2) ◽  
Author(s):  
M Kawka ◽  
A M Dawidziuk ◽  
L R Jiao ◽  
T M H Gall
Keyword(s):  
Artificial Intelligence ◽  
Hepatocellular Carcinoma ◽  
Clinical Decision Making ◽  
Interdisciplinary Collaboration ◽  
Small Sample Size ◽  
External Validation ◽  
Small Sample ◽  
Cochrane Library ◽  
Original Research ◽  
Qualitative Synthesis

Abstract Introduction Hepatocellular carcinoma (HCC) is a significant cause of morbidity and mortality worldwide. Despite significant advancements, the diagnosis and management of HCC remain a challenge. This review aims at exploring artificial intelligence (AI) solutions applied to HCC. Method A review of the literature from Embase, MEDLINE and Cochrane Library was conducted to determine the role of AI in HCC, across three domains: detection, characterisation, and prediction. 56 relevant original research studies were identified and included in a qualitative synthesis. Results AI models can be implemented into detection of HCC, as they excel at analysis and integration of large datasets. Moreover, AI outclasses traditional statistical models at tumour characterisation based on radiological and pathological images. Predicting treatment outcomes and survival using AI can shape future HCC guidelines and support clinical decision making, especially treatment choice. AI in HCC has limitations, hindering its clinical adoption. Small sample size, single-centre data, non-transparent reporting, lack of external validation, and overfitting all results in low generalisability of findings. Conclusions AI has immense potential; however, interdisciplinary collaboration is needed to improve, validate, and implement it across all aspects of HCC. AI has a multifaceted role in HCC and its importance can increase in the future, as more sophisticated technologies emerge.

scholarly journals Artificial Intelligence for COVID-19: Rapid Review (Preprint)

2020 ◽  
Author(s):  
Jiayang Chen ◽  
Kay Choong See
Keyword(s):  
Artificial Intelligence ◽  
English Language ◽  
Clinical Decision Making ◽  
External Validation ◽  
Clinical Decision ◽  
Rapid Review ◽  
Reference List ◽  
Health Crisis ◽  
Language Studies ◽  
Multimodal Methods

BACKGROUND COVID-19 was first discovered in December 2019 and has since evolved into a pandemic. OBJECTIVE To address this global health crisis, artificial intelligence (AI) has been deployed at various levels of the health care system. However, AI has both potential benefits and limitations. We therefore conducted a review of AI applications for COVID-19. METHODS We performed an extensive search of the PubMed and EMBASE databases for COVID-19–related English-language studies published between December 1, 2019, and March 31, 2020. We supplemented the database search with reference list checks. A thematic analysis and narrative review of AI applications for COVID-19 was conducted. RESULTS In total, 11 papers were included for review. AI was applied to COVID-19 in four areas: diagnosis, public health, clinical decision making, and therapeutics. We identified several limitations including insufficient data, omission of multimodal methods of AI-based assessment, delay in realization of benefits, poor internal/external validation, inability to be used by laypersons, inability to be used in resource-poor settings, presence of ethical pitfalls, and presence of legal barriers. AI could potentially be explored in four other areas: surveillance, combination with big data, operation of other core clinical services, and management of patients with COVID-19. CONCLUSIONS In view of the continuing increase in the number of cases, and given that multiple waves of infections may occur, there is a need for effective methods to help control the COVID-19 pandemic. Despite its shortcomings, AI holds the potential to greatly augment existing human efforts, which may otherwise be overwhelmed by high patient numbers.

scholarly journals Rummage of Machine Learning Algorithms in Cancer Diagnosis

2021 ◽  
Vol 12 (1) ◽  
pp. 1-15
Author(s):  
Prashant Johri ◽  
Vivek sen Saxena ◽  
Avneesh Kumar
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Clinical Decision Making ◽  
Learning Algorithms ◽  
Clinical Decision ◽  
Machine Learning Algorithms ◽  
Healthcare Sector ◽  
Healthcare Data ◽  
Digital Imaging Technology ◽  
Health Studies

With the continuous improvement of digital imaging technology and rapid increase in the use of digital medical records in last decade, artificial intelligence has provided various techniques to analyze these data. Machine learning, a subset of artificial intelligence techniques, provides the ability to learn from past and present and to predict the future on the basis of data. Various AI-enabled support systems are designed by using machine learning algorithms in order to optimize and computerize the process of clinical decision making and to bring about a massive archetype change in the healthcare sector such as timely identification, revealing and treatment of disease, as well as outcome prediction. Machine learning algorithms are implemented in the healthcare sector and helped in diagnosis of critical illness such as cancer, neurology, cardiac, and kidney disease as well as with easing in anticipation of disease progression. By applying and executing machine learning algorithms over healthcare data, one can evaluate, analyze, and generate the results that can be used not only to advance the prior health studies but also to aid in forecasting a patient's chances of developing of various diseases. The aim in this article is to present an overview of machine learning and to cover various algorithms of machine learning and their present implementation in the healthcare sector.

scholarly journals Intelligent health system for investigation and consenting COVID-19 patients and precision medicine

2021 ◽  
Author(s):  
Zeeshan Ahmed
Keyword(s):  
Artificial Intelligence ◽  
Clinical Decision Making ◽  
Recovery Process ◽  
Clinical Decision ◽  
Machine Learning Algorithms ◽  
Data Intensive ◽  
Healthcare Data ◽  
Causes Of Mortality ◽  
Data Granularity ◽  
Public Datasets

Advancing frontiers of clinical research, we discuss the need for intelligent health systems to support a deeper investigation of COVID-19. We hypothesize that the convergence of the healthcare data and staggering developments in artificial intelligence have the potential to elevate the recovery process with diagnostic and predictive analysis to identify major causes of mortality, modifiable risk factors and actionable information that supports the early detection and prevention of COVID-19. However, current constraints include the recruitment of COVID-19 patients for research; translational integration of electronic health records and diversified public datasets; and the development of artificial intelligence systems for data-intensive computational modeling to assist clinical decision making. We propose a novel nexus of machine learning algorithms to examine COVID-19 data granularity from population studies to subgroups stratification and ensure best modeling strategies within the data continuum.

Sign in / Sign up

Export Citation Format

Share Document