Search

BackgroundCOVID-19 has overwhelmed health systems worldwide. It is important to identify severe cases as early as possible, such that resources can be mobilized and treatment can be escalated. ObjectiveThis study aims to develop a machine learning approach for automated severity assessment of COVID-19 based on clinical and imaging data. MethodsClinical data—including demographics, signs, symptoms, comorbidities, and blood test results—and chest computed tomography scans of 346 patients from 2 hospitals in the Hubei Province, China, were used to develop machine learning models for automated severity assessment in diagnosed COVID-19 cases. We compared the predictive power of the clinical and imaging data from multiple machine learning models and further explored the use of four oversampling methods to address the imbalanced classification issue. Features with the highest predictive power were identified using the Shapley Additive Explanations framework. ResultsImaging features had the strongest impact on the model output, while a combination of clinical and imaging features yielded the best performance overall. The identified predictive features were consistent with those reported previously. Although oversampling yielded mixed results, it achieved the best model performance in our study. Logistic regression models differentiating between mild and severe cases achieved the best performance for clinical features (area under the curve [AUC] 0.848; sensitivity 0.455; specificity 0.906), imaging features (AUC 0.926; sensitivity 0.818; specificity 0.901), and a combination of clinical and imaging features (AUC 0.950; sensitivity 0.764; specificity 0.919). The synthetic minority oversampling method further improved the performance of the model using combined features (AUC 0.960; sensitivity 0.845; specificity 0.929). ConclusionsClinical and imaging features can be used for automated severity assessment of COVID-19 and can potentially help triage patients with COVID-19 and prioritize care delivery to those at a higher risk of severe disease.

BackgroundSmartphone apps, fitness trackers, and online social networks have shown promise in weight management and physical activity interventions. However, there are knowledge gaps in identifying the most effective and engaging interventions and intervention features preferred by their users. ObjectiveThis 6-month pilot study on a social networking mobile app connected to wireless weight and activity tracking devices has 2 main aims: to evaluate changes in BMI, weight, and physical activity levels in users from different BMI categories and to assess user perspectives on the intervention, particularly on social comparison and automated self-monitoring and feedback features. MethodsThis was a mixed methods study involving a one-arm, pre-post quasi-experimental pilot with postintervention interviews and focus groups. Healthy young adults used a social networking mobile app intervention integrated with wireless tracking devices (a weight scale and a physical activity tracker) for 6 months. Quantitative results were analyzed separately for 2 groups—underweight-normal and overweight-obese BMI—using t tests and Wilcoxon sum rank, Wilcoxon signed rank, and chi-square tests. Weekly BMI change in participants was explored using linear mixed effects analysis. Interviews and focus groups were analyzed inductively using thematic analysis. ResultsIn total, 55 participants were recruited (mean age of 23.6, SD 4.6 years; 28 women) and 45 returned for the final session (n=45, 82% retention rate). There were no differences in BMI from baseline to postintervention (6 months) and between the 2 BMI groups. However, at 4 weeks, participants’ BMI decreased by 0.34 kg/m2 (P

BackgroundHaving patients self-manage their health conditions is a widely promoted concept, but many patients struggle to practice it effectively. Moreover, few studies have analyzed the nature of work required from patients and how such work fits into the context of their daily life. ObjectiveThis study aimed to review the characteristics of patient work in adult patients. Patient work refers to tasks that health conditions impose on patients (eg, taking medications) within a system of contextual factors. MethodsA systematic scoping review was conducted using narrative synthesis. Data were extracted from PubMed, Excerpta Medica database (EMBASE), Cumulative Index to Nursing and Allied Health Literature (CINAHL), and PsycINFO, including studies from August 2013 to August 2018. The included studies focused on adult patients and assessed one or more of the following: (1) physical health–related tasks, (2) cognitive health–related tasks, or (3) contextual factors affecting these tasks. Tasks were categorized according to the themes that emerged: (1) if the task is always visible to others or can be cognitive, (2) if the task must be conducted collaboratively or can be conducted alone, and (3) if the task was done with the purpose of creating resources. Contextual factors were grouped according to the level at which they exert influence (micro, meso, or macro) and where they fit in the patient work system (the macroergonomic layer of physical, social, and organizational factors; the mesoergonomic layer of household and community; and the microergonomic triad of person-task-tools). ResultsIn total, 67 publications were included, with 58 original research articles and 9 review articles. A variety of patient work tasks were observed, ranging from physical and tangible tasks (such as taking medications and visiting health care professionals) to psychological and social tasks (such as creating coping strategies). Patient work was affected by a range of contextual factors on the micro, meso, or macro levels. Our results indicate that most patient work was done alone, in private, and often imposing cognitive burden with low amounts of support. ConclusionsThis review sought to provide insight into the work burden of health management from a patient perspective and how patient context influences such work. For many patients, health-related work is ever present, invisible, and overwhelming. When researchers and clinicians design and implement patient-facing interventions, it is important to understand how the extra work impacts one’s internal state and coping strategy, how such work fits into daily routines, and if these changes could be maintained in the long term.

BackgroundConversational agents (CAs) are systems that mimic human conversations using text or spoken language. Their widely used examples include voice-activated systems such as Apple Siri, Google Assistant, Amazon Alexa, and Microsoft Cortana. The use of CAs in health care has been on the rise, but concerns about their potential safety risks often remain understudied. ObjectiveThis study aimed to analyze how commonly available, general-purpose CAs on smartphones and smart speakers respond to health and lifestyle prompts (questions and open-ended statements) by examining their responses in terms of content and structure alike. MethodsWe followed a piloted script to present health- and lifestyle-related prompts to 8 CAs. The CAs’ responses were assessed for their appropriateness on the basis of the prompt type: responses to safety-critical prompts were deemed appropriate if they included a referral to a health professional or service, whereas responses to lifestyle prompts were deemed appropriate if they provided relevant information to address the problem prompted. The response structure was also examined according to information sources (Web search–based or precoded), response content style (informative and/or directive), confirmation of prompt recognition, and empathy. ResultsThe 8 studied CAs provided in total 240 responses to 30 prompts. They collectively responded appropriately to 41% (46/112) of the safety-critical and 39% (37/96) of the lifestyle prompts. The ratio of appropriate responses deteriorated when safety-critical prompts were rephrased or when the agent used a voice-only interface. The appropriate responses included mostly directive content and empathy statements for the safety-critical prompts and a mix of informative and directive content for the lifestyle prompts. ConclusionsOur results suggest that the commonly available, general-purpose CAs on smartphones and smart speakers with unconstrained natural language interfaces are limited in their ability to advise on both the safety-critical health prompts and lifestyle prompts. Our study also identified some response structures the CAs employed to present their appropriate responses. Further investigation is needed to establish guidelines for designing suitable response structures for different prompt types.

Although much effort is focused on improving the technical performance of artificial intelligence, there are compelling reasons to focus more on the implementation of this technology class to solve real-world applications. In this “last mile” of implementation lie many complex challenges that may make technically high-performing systems perform poorly. Instead of viewing artificial intelligence development as a linear one of algorithm development through to eventual deployment, there are strong reasons to take a more agile approach, iteratively developing and testing artificial intelligence within the context in which it finally will be used.

BackgroundThe personalization of conversational agents with natural language user interfaces is seeing increasing use in health care applications, shaping the content, structure, or purpose of the dialogue between humans and conversational agents. ObjectiveThe goal of this systematic review was to understand the ways in which personalization has been used with conversational agents in health care and characterize the methods of its implementation. MethodsWe searched on PubMed, Embase, CINAHL, PsycInfo, and ACM Digital Library using a predefined search strategy. The studies were included if they: (1) were primary research studies that focused on consumers, caregivers, or health care professionals; (2) involved a conversational agent with an unconstrained natural language interface; (3) tested the system with human subjects; and (4) implemented personalization features. ResultsThe search found 1958 publications. After abstract and full-text screening, 13 studies were included in the review. Common examples of personalized content included feedback, daily health reports, alerts, warnings, and recommendations. The personalization features were implemented without a theoretical framework of customization and with limited evaluation of its impact. While conversational agents with personalization features were reported to improve user satisfaction, user engagement and dialogue quality, the role of personalization in improving health outcomes was not assessed directly. ConclusionsMost of the studies in our review implemented the personalization features without theoretical or evidence-based support for them and did not leverage the recent developments in other domains of personalization. Future research could incorporate personalization as a distinct design factor with a more careful consideration of its impact on health outcomes and its implications on patient safety, privacy, and decision-making.

BackgroundTechnological interventions such as mobile apps, Web-based social networks, and wearable trackers have the potential to influence physical activity; yet, only a few studies have examined the efficacy of an intervention bundle combining these different technologies. ObjectiveThis study aimed to pilot test an intervention composed of a social networking mobile app, connected with a wearable tracker, and investigate its efficacy in improving physical activity, as well as explore participant engagement and the usability of the app. MethodsThis was a pre-post quasi-experimental study with 1 arm, where participants were subjected to the intervention for a 6-month period. The primary outcome measure was the difference in daily step count between baseline and 6 months. Secondary outcome measures included engagement with the intervention and system usability. Descriptive and inferential statistical tests were conducted; posthoc subgroup analyses were carried out for participants with different levels of steps at baseline, app usage, and social features usage. ResultsA total of 55 participants were enrolled in the study; the mean age was 23.6 years and 28 (51%) were female. There was a nonstatistically significant increase in the average daily step count between baseline and 6 months (mean change=14.5 steps/day, P=.98, 95% CI –1136.5 to 1107.5). Subgroup analysis comparing the higher and lower physical activity groups at baseline showed that the latter had a statistically significantly higher increase in their daily step count (group difference in mean change from baseline to 6 months=3025 steps per day, P=.008, 95% CI 837.9-5211.8). At 6 months, the retention rate was 82% (45/55); app usage decreased over time. The mean system usability score was 60.1 (SD 19.2). ConclusionsThis study showed the preliminary efficacy of a mobile social networking intervention, integrated with a wearable tracker to promote physical activity, particularly for less physically active subgroups of the population. Future research should explore how to address challenges faced by physically inactive people to provide tailored advices. In addition, users’ perspectives should be explored to shed light on factors that might influence their engagement with the intervention.

BackgroundGroups and individuals that seek to negatively influence public opinion about the safety and value of vaccination are active in online and social media and may influence decision making within some communities. ObjectiveWe sought to measure whether exposure to negative opinions about human papillomavirus (HPV) vaccines in Twitter communities is associated with the subsequent expression of negative opinions by explicitly measuring potential information exposure over the social structure of Twitter communities. MethodsWe hypothesized that prior exposure to opinions rejecting the safety or value of HPV vaccines would be associated with an increased risk of posting similar opinions and tested this hypothesis by analyzing temporal sequences of messages posted on Twitter (tweets). The study design was a retrospective analysis of tweets related to HPV vaccines and the social connections between users. Between October 2013 and April 2014, we collected 83,551 English-language tweets that included terms related to HPV vaccines and the 957,865 social connections among 30,621 users posting or reposting the tweets. Tweets were classified as expressing negative or neutral/positive opinions using a machine learning classifier previously trained on a manually labeled sample. ResultsDuring the 6-month period, 25.13% (20,994/83,551) of tweets were classified as negative; among the 30,621 users that tweeted about HPV vaccines, 9046 (29.54%) were exposed to a majority of negative tweets. The likelihood of a user posting a negative tweet after exposure to a majority of negative opinions was 37.78% (2780/7361) compared to 10.92% (1234/11,296) for users who were exposed to a majority of positive and neutral tweets corresponding to a relative risk of 3.46 (95% CI 3.25-3.67, P

In 2014, the vast majority of published biomedical research is still hidden behind paywalls rather than open access. For more than a decade, similar restrictions over other digitally available content have engendered illegal activity. Music file sharing became rampant in the late 1990s as communities formed around new ways to share. The frequency and scale of cyber-attacks against commercial and government interests has increased dramatically. Massive troves of classified government documents have become public through the actions of a few. Yet we have not seen significant growth in the illegal sharing of peer-reviewed academic articles. Should we truly expect that biomedical publishing is somehow at less risk than other content-generating industries? What of the larger threat—a “Biblioleaks” event—a database breach and public leak of the substantial archives of biomedical literature? As the expectation that all research should be available to everyone becomes the norm for a younger generation of researchers and the broader community, the motivations for such a leak are likely to grow. We explore the feasibility and consequences of a Biblioleaks event for researchers, journals, publishers, and the broader communities of doctors and the patients they serve.

BackgroundPersonally controlled health management systems (PCHMSs) contain a bundle of features to help patients and consumers manage their health. However, it is unclear how consumers actually use a PCHMS in their everyday settings. ObjectiveTo conduct an empirical analysis of how consumers used the social (forum and poll) and self-reflective (diary and personal health record [PHR]) features of a Web-based PCHMS designed to support their physical and emotional well-being. MethodsA single-group pre/post-test online prospective study was conducted to measure use of a Web-based PCHMS for physical and emotional well-being needs during a university academic semester. The PCHMS integrated an untethered PHR with social forums, polls, a diary, and online messaging links with a health service provider. Well-being journeys additionally provided information to encourage engagement with clinicians and health services. A total of 1985 students and staff aged 18 and above with access to the Internet were recruited online, of which 709 were eligible for analysis. Participants’ self-reported well-being, health status, health service utilization, and help-seeking behaviors were compared using chi-square, McNemar’s test, and Student’s t test. Social networks were constructed to examine the online forum communication patterns among consumers and clinicians. ResultsThe two PCHMS features that were used most frequently and considered most useful and engaging were the social features (ie, the poll and forum). More than 30% (213/709) of participants who sought well-being assistance during the study indicated that other people had influenced their decision to seek help (54.4%, 386/709 sought assistance for physical well-being; 31.7%, 225/709 for emotional well-being). Although the prevalence of using a self-reflective feature (diary or PHR) was not as high (diary: 8.6%, 61/709; PHR: 15.0%, 106/709), the proportion of participants who visited a health care professional during the study was more than 20% greater in the group that did use a self-reflective feature (diary: P=.03; PHR: P

BackgroundMany studies have shown the effectiveness of self-management for patients with asthma. In particular, possession and use of a written asthma action plan provided by a doctor has shown to significantly improve patients’ asthma control. Yet, uptake of a written asthma action plan and preventative asthma management is low in the community, especially amongst adults. ObjectiveA Web-based personally controlled health management system (PCHMS) called Healthy.me will be evaluated in a 2010 CONSORT-compliant 2-group (static websites verse PCHMS) parallel randomized controlled trial (RCT) (allocation ratio 1:1). MethodsThe PCHMS integrates an untethered personal health record with consumer care pathways and social forums. After eligibility assessment, a sample of 300 adult patients with moderate persistent asthma will be randomly assigned to one of these arms. After 12 months of using either Healthy.me or information websites (usual care arm), a post-study assessment will be conducted. ResultsThe primary outcome measure is possession of or revision of an asthma action plan during the study. Secondary outcome measures include: (1) adherence to the asthma action plan, (2) rate of planned and unplanned visits to healthcare providers for asthma issues, (3) usage patterns of Healthy.me and attrition rates, (4) asthma control and asthma exacerbation scores, and (5) impact of asthma on life and competing demands, and days lost from work. ConclusionsThis RCT will provide insights into whether access to an online PCHMS will improve uptake of a written asthma action plan and preventative asthma actions. Trial RegistrationTrial Registration: Australian New Zealand Clinical Trials Registry ACTRN12612000716864; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=362714 (Archived by WebCite at http://www.webcitation.org/6IYBJGRnW).

BackgroundPersonally controlled health management systems (PCHMS), which include a personal health record (PHR), health management tools, and consumer resources, represent the next stage in consumer eHealth systems. It is still unclear, however, what features contribute to an engaging and efficacious PCHMS. ObjectiveTo identify features in a Web-based PCHMS that are associated with consumer utilization of primary care and counselling services, and help-seeking rates for physical and emotional well-being concerns. MethodsA one-group pre/posttest online prospective study was conducted on a university campus to measure use of a PCHMS for physical and emotional well-being needs during a university academic semester (July to November 2011). The PCHMS integrated an untethered personal health record (PHR) with well-being journeys, social forums, polls, diaries, and online messaging links with a health service provider, where journeys provide information for consumer participants to engage with clinicians and health services in an actionable way. 1985 students and staff aged 18 and above with access to the Internet were recruited online. Logistic regression, the Pearson product-moment correlation coefficient, and chi-square analyses were used to associate participants’ help-seeking behaviors and health service utilization with PCHMS usage among the 709 participants eligible for analysis. ResultsA dose-response association was detected between the number of times a user logged into the PCHMS and the number of visits to a health care professional (P=.01), to the university counselling service (P=.03), and help-seeking rates (formal or informal) for emotional well-being matters (P=.03). No significant association was detected between participant pre-study characteristics or well-being ratings at different PCHMS login frequencies. Health service utilization was strongly correlated with use of a bundle of features including: online appointment booking (primary care: OR 1.74, 95% CI 1.01-3.00; counselling: OR 6.04, 95% CI 2.30-15.85), personal health record (health care professional: OR 2.82, 95% CI 1.63-4.89), the poll (health care professional: OR 1.47, 95% CI 1.02-2.12), and diary (counselling: OR 4.92, 95% CI 1.40-17.35). Help-seeking for physical well-being matters was only correlated with use of the personal health record (OR 1.73, 95% CI 1.18-2.53). Help-seeking for emotional well-being concerns (including visits to the university counselling service) was correlated with a bundle comprising the poll (formal or informal help-seeking: OR 1.03, 95% CI 1.00-1.05), diary (counselling: OR 4.92, 95% CI 1.40-17.35), and online appointment booking (counselling: OR 6.04, 95% CI 2.30-15.85). ConclusionsFrequent usage of a PCHMS was significantly associated with increased consumer health service utilization and help-seeking rates for emotional health matters in a university sample. Different bundles of PCHMS features were associated with physical and emotional well-being matters. PCHMS appears to be a promising mechanism to engage consumers in help-seeking or health service utilization for physical and emotional well-being matters.

BackgroundSearching the Web for documents using information retrieval systems plays an important part in clinicians’ practice of evidence-based medicine. While much research focuses on the design of methods to retrieve documents, there has been little examination of the way different search engine capabilities influence clinician search behaviors. ObjectivesPrevious studies have shown that use of task-based search engines allows for faster searches with no loss of decision accuracy compared with resource-based engines. We hypothesized that changes in search behaviors may explain these differences. MethodsIn all, 75 clinicians (44 doctors and 31 clinical nurse consultants) were randomized to use either a resource-based or a task-based version of a clinical information retrieval system to answer questions about 8 clinical scenarios in a controlled setting in a university computer laboratory. Clinicians using the resource-based system could select 1 of 6 resources, such as PubMed; clinicians using the task-based system could select 1 of 6 clinical tasks, such as diagnosis. Clinicians in both systems could reformulate search queries. System logs unobtrusively capturing clinicians’ interactions with the systems were coded and analyzed for clinicians’ search actions and query reformulation strategies. ResultsThe most frequent search action of clinicians using the resource-based system was to explore a new resource with the same query, that is, these clinicians exhibited a “breadth-first” search behaviour. Of 1398 search actions, clinicians using the resource-based system conducted 401 (28.7%, 95% confidence interval [CI] 26.37-31.11) in this way. In contrast, the majority of clinicians using the task-based system exhibited a “depth-first” search behavior in which they reformulated query keywords while keeping to the same task profiles. Of 585 search actions conducted by clinicians using the task-based system, 379 (64.8%, 95% CI 60.83-68.55) were conducted in this way. ConclusionsThis study provides evidence that different search engine designs are associated with different user search behaviors.

Background Provision of online evidence at the point of care is one strategy that could provide clinicians with easy access to up-to-date evidence in clinical settings in order to support evidence-based decision making. ObjectiveThe aim was to determine long-term use of an online evidence system in routine clinical practice. MethodsThis was a prospective cohort study. 59 clinicians who had a computer with Internet access in their consulting room participated in a 12-month trial of Quick Clinical, an online evidence system specifically designed around the needs of general practitioners (GPs). Patterns of use were determined by examination of computer logs and survey analysis. ResultsOn average, 9.9 searches were conducted by each GP in the first 2 months of the study. After this, usage dropped to 4.4 searches per GP in the third month and then levelled off to between 0.4 and 2.6 searches per GP per month. The majority of searches (79.2%, 2013/2543) were conducted during practice hours (between 9 am and 5 pm) and on weekdays (90.7%, 2315/2543). The most frequent searches related to diagnosis (33.6%, 821/2291) and treatment (34.5%, 844/2291). Conclusion GPs will use an online evidence retrieval system in routine practice; however, usage rates drop significantly after initial introduction of the system. Long-term studies are required to determine the extent to which GPs will integrate the use of such technologies into their everyday clinical practice and how this will affect the satisfaction and health outcomes of their patients.

BackgroundThe World Wide Web has increasingly become an important source of information in health care consumer decision making. However, little is known about whether searching online resources actually improves consumers’ understanding of health issues. ObjectivesThe aim was to study whether searching on the World Wide Web improves consumers’ accuracy in answering health questions and whether consumers’ understanding of health issues is subject to further change under social feedback. MethodsThis was a pre/post prospective online study. A convenience sample of 227 undergraduate students was recruited from the population of the University of New South Wales. Subjects used a search engine that retrieved online documents from PubMed, MedlinePlus, and HealthInsite and answered a set of six questions (before and after use of the search engine) designed for health care consumers. They were then presented with feedback consisting of a summary of the post-search answers provided by previous subjects for the same questions and were asked to answer the questions again. ResultsThere was an improvement in the percentage of correct answers after searching (pre-search 61.2% vs post-search 82.0%, P