The advent of ChatGPT has sparked a heated debate surrounding natural language processing technology and AI-powered chatbots, leading to extensive research and applications across various disciplines. This pilot study aims to investigate the impact of ChatGPT on users' experiences by administering two distinct questionnaires, one generated by humans and the other by ChatGPT, along with an Emotion Detecting Model. A total of 14 participants (7 female and 7 male) aged between 18 and 35 years were recruited, resulting in the collection of 8672 ChatGPT-associated data points and 8797 human-associated data points. Data analysis was conducted using Analysis of Variance (ANOVA). The results indicate that the utilization of ChatGPT enhances participants' happiness levels and reduces their sadness levels. While no significant gender influences were observed, variations were found about specific emotions. It is important to note that the limited sample size, narrow age range, and potential cultural impacts restrict the generalizability of the findings to a broader population. Future research directions should explore the impact of incorporating additional language models or chatbots on user emotions, particularly among specific age groups such as older individuals and teenagers. As one of the pioneering works evaluating the human perception of ChatGPT text and communication, it is noteworthy that ChatGPT received positive evaluations and demonstrated effectiveness in generating extensive questionnaires.
Emotions , Happiness , Adolescent , Humans , Female , Male , Young Adult , Adult , Pilot Projects , Sadness , Perception
Sleep disorders are prevalent nowadays, leading to anxiety, depression, high blood pressure, and other health problems. Due to the proliferation of mobile devices and the development of communication technologies, mobile apps have become a popular way to deliver sleep disorder therapy or manage sleep. This scoping review aims to conduct a systematic investigation of mobile apps and technologies supporting sleep, including the essential functions of sleep apps, how they are used to improve sleep and the facilitators of and barriers to using apps among patients and other stakeholders. We searched articles (2010 to 2022) from Scopus, Web of Science, Science Direct, PubMed, and IEEE Xplore using the keyword sleep apps. In total, 1,650 peer-reviewed articles were screened, and 51 were selected for inclusion. The most frequently provided functions by the apps are sleep monitoring, measuring sleep, providing alarms, and recording sleep using a sleep diary. Several wearable devices have been used with mobile apps to record sleep duration and sleep problems. Facilitators and barriers to using apps were identified, along with the evidence-based design guidelines. Existing studies have proved the initial validation and efficiency of delivering sleep treatment by mobile apps; however, more research is needed to improve the performance of sleep apps and devise a way to utilize them as a therapy tool.
Childhood obesity is a widespread medical condition and presents a formidable challenge for public health. Long-term treatment strategies and early prevention strategies are required because obese children are more likely to carry this condition into adulthood, increasing their risk of developing other major health disorders. The present review analyses various technological interventions available for childhood obesity prevention and treatment. It also examines whether machine learning and technological interventions can play vital roles in its management. Twenty-six studies were shortlisted for the review using various technological strategies and analysed regarding their efficacy. While most of the selected studies showed positive outcomes, there was a lack of studies using robots and artificial intelligence to manage obesity in children. The use of machine learning was observed in various studies, and the integration of social robots and other efficacious strategies may be effective for treating childhood obesity in the future.
This work introduces a predictive Length of Stay (LOS) framework for lung cancer patients using machine learning (ML) models. The framework proposed to deal with imbalanced datasets for classification-based approaches using electronic healthcare records (EHR). We have utilized supervised ML methods to predict lung cancer inpatients LOS during ICU hospitalization using the MIMIC-III dataset. Random Forest (RF) Model outperformed other models and achieved predicted results during the three framework phases. With clinical significance features selection, over-sampling methods (SMOTE and ADASYN) achieved the highest AUC results (98% with CI 95%: 95.3-100%, and 100% respectively). The combination of Over-sampling and under-sampling achieved the second-highest AUC results (98%, with CI 95%: 95.3-100%, and 97%, CI 95%: 93.7-100% SMOTE-Tomek, and SMOTE-ENN respectively). Under-sampling methods reported the least important AUC results (50%, with CI 95%: 40.2-59.8%) for both (ENN and Tomek- Links). Using ML explainable technique called SHAP, we explained the outcome of the predictive model (RF) with SMOTE class balancing technique to understand the most significant clinical features that contributed to predicting lung cancer LOS with the RF model. Our promising framework allows us to employ ML techniques in-hospital clinical information systems to predict lung cancer admissions into ICU.
Length of Stay , Lung Neoplasms , Machine Learning , Humans
AIMS AND OBJECTIVES: Stroke is the main cause of long-term disability and happens mostly in the older population. Stroke affected patients experience either of the cognitive, visual or motor losses and recovery requires time and patience as they have to do physical exercises every day and at times repetitively. There are various types of stroke rehabilitation exercises focussing on technological solutions that include therapies performed using games. Motion-based games are popular in encouraging participants to perform repetitive tasks without being getting bored. Therefore, in this study, we have explored studies that included the use of games for stroke rehabilitation to understand the design principles and characteristics of the games used for these purposes. METHOD: A number of medical respositories were searched for relevant articles in a window of 2008-2018. 18 studies were chosen for the scoping review depending on the inclusion criteria, and design principles used in these studies are analysed and evaluated. RESULTS AND CONCLUSION: We present main findings from our review concerning the attributes of existing games for stroke rehabilitation such as meaningful play, handling of failures, emphasising challenge, and the value of feedback. We conclude with a list of design recommendations that future serious game developers can consider while designing interfaces for stroke patients.Implications for RehabilitationThis review exhibits that the usage of gaming technologies is a very effective interactive mechanism for stroke based rehabilitation.Further our review also shows that serious games provide an avenue and opportunity for customized and highly contextualized gameplayOur review also suggests that effective features to incorporate into serious games for rehabilitation includes; facilitating challenge and recovery from errors.
Stroke Rehabilitation , Stroke , Video Games , Humans , Video Games/psychology
Services are intangible in nature and as a result, it is often difficult to measure the quality of the service. In the service literature, the service is usually delivered by a human to a human customer and the quality of the service is often evaluated using the SERVQUAL dimensions. An extensive review of the literature shows there is a lack of an empirical model to assess the perceived service quality provided by a social robot. Furthermore, the social robot literature highlights key differences between human service and social robots. For example, scholars have highlighted the importance of entertainment value and engagement in the adoption of social robots in the service industry. However, it is unclear whether the SERVQUAL dimensions are appropriate to measure social robot's service quality. The paper proposes the SERVBOT model to assess a social robot's service quality. It identifies, reliability, responsiveness, assurance, empathy, and entertainment as the five dimensions of SERVBOT. Further, the research will investigate how these five factors influence emotional engagement and future intentions to use the social robot in a concierge service setting. The model was tested using student sampling, and a total of 94 responses were collected for the study. The findings indicate empathy and entertainment value as key predictors of emotional engagement. Further, emotional engagement is a strong predictor of future intention to use a social robot in a service setting. This study is the first to propose the SERVBOT model to measure social robot's service quality. The model provides a theoretical underpinning on the key service quality dimensions of a social robot and gives scholars and managers a method to track the service quality of a social robot. The study also extends on the literature by exploring the key factors that influence the use of social robots (i.e., emotional engagement).
COVID-19 as a global pandemic has had an unprecedented impact on the entire world. Projecting the future spread of the virus in relation to its characteristics for a specific suite of countries against a temporal trend can provide public health guidance to governments and organizations. Therefore, this paper presented an epidemiological comparison of the traditional SEIR model with an extended and modified version of the same model by splitting the infected compartment into asymptomatic mild and symptomatic severe. We then exposed our derived layered model into two distinct case studies with variations in mitigation strategies and non-pharmaceutical interventions (NPIs) as a matter of benchmarking and comparison. We focused on exploring the United Arab Emirates (a small yet urban centre (where clear sequential stages NPIs were implemented). Further, we concentrated on extending the models by utilizing the effective reproductive number (R t) estimated against time, a more realistic than the static R 0, to assess the potential impact of NPIs within each case study. Compared to the traditional SEIR model, the results supported the modified model as being more sensitive in terms of peaks of simulated cases and flattening determinations.
BACKGROUND: Many countries across the globe have released their own COVID-19 contact tracing apps. This has resulted in the proliferation of several apps that used a variety of technologies. With the absence of a standardized approach used by the authorities, policy makers, and developers, many of these apps were unique. Therefore, they varied by function and the underlying technology used for contact tracing and infection reporting. OBJECTIVE: The goal of this study was to analyze most of the COVID-19 contact tracing apps in use today. Beyond investigating the privacy features, design, and implications of these apps, this research examined the underlying technologies used in contact tracing apps. It also attempted to provide some insights into their level of penetration and to gauge their public reception. This research also investigated the data collection, reporting, retention, and destruction procedures used by each of the apps under review. METHODS: This research study evaluated 13 apps corresponding to 10 countries based on the underlying technology used. The inclusion criteria ensured that most COVID-19-declared epicenters (ie, countries) were included in the sample, such as Italy. The evaluated apps also included countries that did relatively well in controlling the outbreak of COVID-19, such as Singapore. Informational and unofficial contact tracing apps were excluded from this study. A total of 30,000 reviews corresponding to the 13 apps were scraped from app store webpages and analyzed. RESULTS: This study identified seven distinct technologies used by COVID-19 tracing apps and 13 distinct apps. The United States was reported to have released the most contact tracing apps, followed by Italy. Bluetooth was the most frequently used underlying technology, employed by seven apps, whereas three apps used GPS. The Norwegian, Singaporean, Georgian, and New Zealand apps were among those that collected the most personal information from users, whereas some apps, such as the Swiss app and the Italian (Immuni) app, did not collect any user information. The observed minimum amount of time implemented for most of the apps with regard to data destruction was 14 days, while the Georgian app retained records for 3 years. No significant battery drainage issue was reported for most of the apps. Interestingly, only about 2% of the reviewers expressed concerns about their privacy across all apps. The number and frequency of technical issues reported on the Apple App Store were significantly more than those reported on Google Play; the highest was with the New Zealand app, with 27% of the reviewers reporting technical difficulties (ie, 10% out of 27% scraped reviews reported that the app did not work). The Norwegian, Swiss, and US (PathCheck) apps had the least reported technical issues, sitting at just below 10%. In terms of usability, many apps, such as those from Singapore, Australia, and Switzerland, did not provide the users with an option to sign out from their apps. CONCLUSIONS: This article highlighted the fact that COVID-19 contact tracing apps are still facing many obstacles toward their widespread and public acceptance. The main challenges are related to the technical, usability, and privacy issues or to the requirements reported by some users.
Attitude , COVID-19/prevention & control , Contact Tracing/methods , Mobile Applications , Privacy , Australia , Data Collection , Disease Outbreaks , Geographic Information Systems , Georgia (Republic) , Humans , Italy , New Zealand , Norway , SARS-CoV-2 , Singapore , Switzerland , Technology , United States , Wireless Technology
The disruption from COVID-19 has been felt deeply across all walks of life. Similarly, academic conferences as one key pillar of dissemination and interaction around research and development have taken a hit. We analyse an interesting focal point as to how conferences in the area of Computer Science have reacted to this disruption with respect to their mode of offering and registration prices, and whether their response is contingent upon specific factors such as where the conference was to be hosted, its ranking, its publisher or its original scheduled date. To achieve this, we collected metadata associated with 170 conferences in the area of Computer Science and as a means of comparison; 25 Psychology conferences. We show that conferences in the area of Computer Science have demonstrated agility and resilience by progressing to an online mode due to COVID-19 (approximately 76% of Computer Science conferences moved to an online mode), many with no changes in their schedule, particularly those in North America and those with a higher ranking. Whilst registration fees have lowered by an average of 42% due to the onset of COVID-19, conferences still have to facilitate attendance on a large scale due to the logistics and costs involved. In conclusion, we discuss the implications of our findings and speculate what they mean for conferences, including those in Computer Science, in the post-COVID-19 world.
Background: Although research has been done on considering YouTube for dissuading and encouraging unhealthy behaviours such as smoking, less focus has been placed on its role in quitting or cutting down alcohol. This study aims to analyse the alcohol cessation videos available and accessible on YouTube to gain a more in-depth insight into the ways that YouTube as a platform is being used to persuade with relation to alcohol cessation. Methods: We systematically searched for content on YouTube related to alcohol cessation and these videos were analysed and evaluated for the format, themes, specific alcohol cessation advice, and uploader. Results: The results demonstrated that the collected alcohol cessation videos included a fairly even presence of the themes of discussing the negative impacts of alcohol and the benefits of quitting or staying away from it. At the same time, however, we found the videos were not sourced from professional institutions, such as government or anti-alcohol misuse non-government organisations. Conclusion: More research is needed to investigate utilising YouTube to support those looking to quit or cut down alcohol.
Smoking Cessation , Social Media , Smoking , Smoking Cessation/methods , Video Recording
Mobile apps have become increasingly prevalent in modern society, and persuasive technology has a broader market than ever. Mobile-based alcohol cessation apps can promote positive behaviour change in users and improve the overall health of our society. This research aimed to understand the various features users respond to and make design recommendations for alcohol cessation apps. This paper reports on three sources of feedback (user ratings, user reviews, MARS App Quality score) provided on 20 alcohol cessation apps in the Google Play Store. Our findings suggest that self-control type apps received much greater positive user reviews than motivational apps. In addition, this trend was not observed through numeric user ratings. We also speculate on design recommendations for apps that are meant to inhibit alcohol intake.
Cell Phone , Mobile Applications , Alcohol Drinking/prevention & control , Health Behavior , Motivation
Predicting Cardiovascular Length of stay based hospitalization at the time of patients' admitting to the coronary care unit (CCU) or (cardiac intensive care units CICU) is deemed as a challenging task to hospital management systems globally. Recently, few studies examined the length of stay (LOS) predictive analytics for cardiovascular inpatients in ICU. However, there are almost scarcely real attempts utilized machine learning models to predict the likelihood of heart failure patients length of stay in ICU hospitalization. This paper introduces a predictive research architecture to predict Length of Stay (LOS) for heart failure diagnoses from electronic medical records using the state-of-art- machine learning models, in particular, the ensembles regressors and deep learning regression models. Our results showed that the gradient boosting regressor (GBR) outweighed the other proposed models in this study. The GBR reported higher R-squared value followed by the proposed method in this study called Staking Regressor. Additionally, The Random forest Regressor (RFR) was the fastest model to train. Our outcomes suggested that deep learning-based regressor did not achieve better results than the traditional regression model in this study. This work contributes to the field of predictive modelling for electronic medical records for hospital management systems.
Intensive Care Units , Machine Learning , Coronary Care Units , Electronic Health Records , Humans , Length of Stay
COVID-19 has posed an unprecedented global public health threat and caused a significant number of severe cases that necessitated long hospitalization and overwhelmed health services in the most affected countries. In response, governments initiated a series of non-pharmaceutical interventions (NPIs) that led to severe economic and social impacts. The effect of these intervention measures on the spread of the COVID-19 pandemic are not well investigated within developing country settings. This study simulated the trajectories of the COVID-19 pandemic curve in Jordan between February and May and assessed the effect of Jordan's strict NPI measures on the spread of COVID-19. A modified susceptible, exposed, infected, and recovered (SEIR) epidemic model was utilized. The compartments in the proposed model categorized the Jordanian population into six deterministic compartments: suspected, exposed, infectious pre-symptomatic, infectious with mild symptoms, infectious with moderate to severe symptoms, and recovered. The GLEAMviz client simulator was used to run the simulation model. Epidemic curves were plotted for estimated COVID-19 cases in the simulation model, and compared against the reported cases. The simulation model estimated the highest number of total daily new COVID-19 cases, in the pre-symptomatic compartmental state, to be 65 cases, with an epidemic curve growing to its peak in 49 days and terminating in a duration of 83 days, and a total simulated cumulative case count of 1048 cases. The curve representing the number of actual reported cases in Jordan showed a good pattern compatibility to that in the mild and moderate to severe compartmental states. The reproduction number under the NPIs was reduced from 5.6 to less than one. NPIs in Jordan seem to be effective in controlling the COVID-19 epidemic and reducing the reproduction rate. Early strict intervention measures showed evidence of containing and suppressing the disease.
Communicable Disease Control/methods , Coronavirus Infections/epidemiology , Pandemics , Pneumonia, Viral/epidemiology , Betacoronavirus , COVID-19 , Computer Simulation , Humans , Jordan/epidemiology , Models, Statistical , SARS-CoV-2 , Severity of Illness Index
Coronavirus Disease 2019 (COVID-19) has affected day to day life and slowed down the global economy. Most countries are enforcing strict quarantine to control the havoc of this highly contagious disease. Since the outbreak of COVID-19, many data analyses have been done to provide close support to decision-makers. We propose a method comprising data analytics and machine learning classification for evaluating the effectiveness of lockdown regulations. Lockdown regulations should be reviewed on a regular basis by governments, to enable reasonable control over the outbreak. The model aims to measure the efficiency of lockdown procedures for various countries. The model shows a direct correlation between lockdown procedures and the infection rate. Lockdown efficiency is measured by finding a correlation coefficient between lockdown attributes and the infection rate. The lockdown attributes include retail and recreation, grocery and pharmacy, parks, transit stations, workplaces, residential, and schools. Our results show that combining all the independent attributes in our study resulted in a higher correlation (0.68) to the dependent value Interquartile 3 (Q3). Mean Absolute Error (MAE) was found to be the least value when combining all attributes.
Coronavirus Infections/prevention & control , Pandemics/prevention & control , Pneumonia, Viral/prevention & control , Quarantine/standards , Betacoronavirus , COVID-19 , Humans , Policy , Quarantine/legislation & jurisprudence , SARS-CoV-2 , Schools
Background and Objective: COVID-19 has engulfed the entire world, with many countries struggling to contain the pandemic. In order to understand how each country is impacted by the virus compared with what would have been expected prior to the pandemic and the mortality risk on a global scale, a multi-factor weighted spatial analysis is presented. Method: A number of key developmental indicators across three main categories of demographics, economy, and health infrastructure were used, supplemented with a range of dynamic indicators associated with COVID-19 as independent variables. Using normalised COVID-19 mortality on 13 May 2020 as a dependent variable, a linear regression (N = 153 countries) was performed to assess the predictive power of the various indicators. Results: The results of the assessment show that when in combination, dynamic and static indicators have higher predictive power to explain risk variation in COVID-19 mortality compared with static indicators alone. Furthermore, as of 13 May 2020 most countries were at a similar or lower risk level than what would have been expected pre-COVID, with only 44/153 countries experiencing a more than 20% increase in mortality risk. The ratio of elderly emerges as a strong predictor but it would be worthwhile to consider it in light of the family makeup of individual countries. Conclusion: In conclusion, future avenues of data acquisition related to COVID-19 are suggested. The paper concludes by discussing the ability of various factors to explain COVID-19 mortality risk. The ratio of elderly in combination with the dynamic variables associated with COVID-19 emerge as more significant risk predictors in comparison to socio-economic and demographic indicators.
Betacoronavirus/isolation & purification , Coronavirus Infections/epidemiology , Pandemics , Pneumonia, Viral/epidemiology , Aged , COVID-19 , Coronavirus Infections/virology , Geography , Humans , Motivation , Pneumonia, Viral/virology , Risk Factors , SARS-CoV-2
The COVID-19 pandemic has caused unprecedented crisis across the world, with many countries struggling with the pandemic. In order to understand how each country is impacted by the virus and assess the risk on a global scale we present a regression based analysis using two pre-existing indexes, namely the Inform and Infectious Disease Vulnerability Index, in conjunction with the number of elderly living in the population. Further we introduce a temporal layer in our modeling by incorporating the stringency level employed by each country over a period of 6 time intervals. Our results show that the indexes and level of stringency are not ideally suited for explaining variation in COVID-19 risk, however the ratio of elderly in the population is a stand out indicator in terms of its predictive power for mortality risk. In conclusion, we discuss how such modeling approaches can assist public health policy.
COVID-19/epidemiology , Pandemics , Risk Assessment , Aged , Health Policy , Humans , Public Health
BACKGROUND: Robot-assisted therapy has become a promising technology in the field of rehabilitation for poststroke patients with motor disorders. Motivation during the rehabilitation process is a top priority for most stroke survivors. With current advancements in technology there has been the introduction of virtual reality (VR), augmented reality (AR), customizable games, or a combination thereof, that aid robotic therapy in retaining, or increasing the interests of, patients so they keep performing their exercises. However, there are gaps in the evidence regarding the transition from clinical rehabilitation to home-based therapy which calls for an updated synthesis of the literature that showcases this trend. The present review proposes a categorization of these studies according to technologies used, and details research in both upper limb and lower limb applications. OBJECTIVE: The goal of this work was to review the practices and technologies implemented in the rehabilitation of poststroke patients. It aims to assess the effectiveness of exoskeleton robotics in conjunction with any of the three technologies (VR, AR, or gamification) in improving activity and participation in poststroke survivors. METHODS: A systematic search of the literature on exoskeleton robotics applied with any of the three technologies of interest (VR, AR, or gamification) was performed in the following databases: MEDLINE, EMBASE, Science Direct & The Cochrane Library. Exoskeleton-based studies that did not include any VR, AR or gamification elements were excluded, but publications from the years 2010 to 2017 were included. Results in the form of improvements in the patients' condition were also recorded and taken into consideration in determining the effectiveness of any of the therapies on the patients. RESULTS: Thirty studies were identified based on the inclusion criteria, and this included randomized controlled trials as well as exploratory research pieces. There were a total of about 385 participants across the various studies. The use of technologies such as VR-, AR-, or gamification-based exoskeletons could fill the transition from the clinic to a home-based setting. Our analysis showed that there were general improvements in the motor function of patients using the novel interfacing techniques with exoskeletons. This categorization of studies helps with understanding the scope of rehabilitation therapies that can be successfully arranged for home-based rehabilitation. CONCLUSIONS: Future studies are necessary to explore various types of customizable games required to retain or increase the motivation of patients going through the individual therapies.
Academic conferences offer numerous submission tracks to support the inclusion of a variety of researchers and topics. Work in progress papers are one such submission type where authors present preliminary results in a poster session. They have recently gained popularity in the area of Human Computer Interaction (HCI) as a relatively easier pathway to attending the conference due to their higher acceptance rate as compared to the main tracks. However, it is not clear if these work in progress papers are further extended or transitioned into more complete and thorough full papers or are simply one-off pieces of research. In order to answer this we explore self-citation patterns of four work in progress editions in two popular HCI conferences (CHI2010, CHI2011, HRI2010 and HRI2011). Our results show that almost 50% of the work in progress papers do not have any self-citations and approximately only half of the self-citations can be considered as true extensions of the original work in progress paper. Specific conferences dominate as the preferred venue where extensions of these work in progress papers are published. Furthermore, the rate of self-citations peaks in the immediate year after publication and gradually tails off. By tracing author publication records, we also delve into possible reasons of work in progress papers not being cited in follow up publications. In conclusion, we speculate on the main trends observed and what they may mean looking ahead for the work in progress track of premier HCI conferences.
