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

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.

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.

Universities are living in a time of major transitions regarding the challenge of rethinking and transforming the current pedagogical models so they can respond to the needs of the global knowmad society. In this study, the Design-Based Research (DBR) approach is used to address the improvements of two emerging pedagogical designs in e-learning in the university context: the model of the Center for Research in Education and ICT (CIIET) of the University of Santiago de Chile (Chile) and the model developed by the Education Node research group of University of Extremadura (Spain). The main focus of these models is the student, who by developing activities based on the resolution of a contextualized problem and using new strategies, accompanied by open resources for resolution, resulting in a learning outcome that can be achieved and measured through assessment. This work aims to advance in identifying of some pedagogical keys for the design of online training scenarios that promote environments of production, research, and open dissemination of best practices, to experience new creative forms and collaborative learning, which have emerged within the hyper connected society and the net-culture.

The number of violent episodes in the Sahel region of Africa, centered around Mali, Burkina Faso, and Niger, has quadrupled from 700 incidents in 2019 to over 2,800 incidents in [...]

Digital competence (DC) is one of the key aspects in citizen development in the digital age. The DC is particularly important in forming university students and future teachers. This article presents the main results of a study to evaluate DC and its relationship with the socioeconomic level of first-year students of pedagogy in three Chilean public universities, located in the north, center, and south of the country. A quantitative research methodology was used, with a sample of 817 students, the data were collected through the DIGCOMP-PED evaluation instrument, which evaluates DC development using the DIGCOMP framework. The results were analyzed at the general and socioeconomic level on the variables of the educational establishment where they attended high school and the territorial area of the university they attended. The main results indicate that the level of DC achievement is intermediate, the areas with the highest levels of achievement were "network security" and "online communication and collaboration." On the other hand, the lowest levels of achievement were reached in the areas "information and digital literacy," "digital content creation," and "problem solving." The level of DC is higher among students of private establishments and those who attend universities located in the central area.

Background Influenza virus remains a threat to human health, but gaps remain in our knowledge of the humoral correlates of protection against influenza virus A/H3N2, limiting our ability to generate effective, broadly protective vaccines. The role of antibodies against the hemagglutinin (HA) stalk, a highly conserved but immunologically subdominant region, has not been established for influenza virus A/H3N2. Methods Household transmission studies were conducted in Managua, Nicaragua, across 3 influenza seasons. Household contacts were tested for influenza virus infection using reverse-transcription polymerase chain reaction. We compared preexisting antibody levels against full-length HA, HA stalk, and neuraminidase (NA) measured by enzyme-linked immunosorbent assay, along with hemagglutination inhibition assay titers, between infected and uninfected participants. Results A total of 899 individuals participated in household activation, with 329 infections occurring. A 4-fold increase in initial HA stalk titers was independently associated with an 18% decrease in the risk of infection (adjusted odds ratio [aOR], 0.82 [95% confidence interval {CI},.68–.98]; P =.04). In adults, anti-HA stalk antibodies were independently associated with protection (aOR, 0.72 [95% CI,.54–.95]; P =.02). However, in 0- to 14-year-olds, anti-NA antibodies (aOR, 0.67 [95% CI,.53–.85]; P <.01) were associated with protection against infection, but anti-HA stalk antibodies were not. Conclusions The HA stalk is an independent correlate of protection against A/H3N2 infection, though this association is age dependent. Our results support the continued exploration of the HA stalk as a target for broadly protective influenza vaccines but suggest that the relative benefits may depend on age and influenza virus exposure history. [ABSTRACT FROM AUTHOR]

Background: The identification of predictors of treatment response is crucial for improving treatment outcome for children with anxiety disorders. Machine learning methods provide opportunities to identify combinations of factors that contribute to risk prediction models. Methods: A machine learning approach was applied to predict anxiety disorder remission in a large sample of 2114 anxious youth (5–18 years). Potential predictors included demographic, clinical, parental, and treatment variables with data obtained pre-treatment, post-treatment, and at least one follow-up. Results: All machine learning models performed similarly for remission outcomes, with AUC between 0.67 and 0.69. There was significant alignment between the factors that contributed to the models predicting two target outcomes: remission of all anxiety disorders and the primary anxiety disorder. Children who were older, had multiple anxiety disorders, comorbid depression, comorbid externalising disorders, received group treatment and therapy delivered by a more experienced therapist, and who had a parent with higher anxiety and depression symptoms, were more likely than other children to still meet criteria for anxiety disorders at the completion of therapy. In both models, the absence of a social anxiety disorder and being treated by a therapist with less experience contributed to the model predicting a higher likelihood of remission. Conclusions: These findings underscore the utility of prediction models that may indicate which children are more likely to remit or are more at risk of non-remission following CBT for childhood anxiety. [ABSTRACT FROM AUTHOR]

This study investigates the relationship between access time to digital technologies and the devel-opment of digital competences among Chilean university students, using the DIGCOMP-PED in-strument based on the DIGCOMP framework. Methods: The instrument was applied to 4360 first-year students at a Chilean public university, and an expert validation process was carried out to identify relevant competences for academic training. Results: The findings indicate a positive but non-linear relationship between years of experience using technologies and performance in certain areas of the DIGCOMP framework. Although the study was conducted between 2021 and 2022, with the follow-up analysis completed in 2024, access alone does not guarantee the acquisition of ad-vanced skills across all competences. Conclusions: The study emphasizes the complexity of the re-lationship between access to technology and the development of digital competences, highlighting the importance of pairing access with quality education and structured guidance in digital literacy to prepare students for the challenges of the digital world. [ABSTRACT FROM AUTHOR]

Objective: To identify factors associated with receiving electroconvulsive therapy (ECT) for serious psychiatric conditions. Methods: Retrospective observational study using hospital administrative data linked with death registrations and outpatient mental health data in New South Wales (NSW), Australia. The cohort included patients admitted with a primary psychiatric diagnosis between 2013 and 2022. The outcome measure was receipt of ECT. Results: Of 94,950 patients, 3465 (3.6%) received ECT. The likelihood of receiving ECT was higher in older (hazard ratio [HR] = 1.03), female (HR = 1.24) patients. Compared to depression, patients with schizophrenia/schizoaffective disorder (HR = 0.79), schizophrenia-related disorders (HR = 0.37), mania (HR = 0.64) and other mood disorders (HR = 0.45) had lower odds of receiving ECT. Patients with depression and one other serious psychiatric condition had higher odds of receiving ECT than depression alone. Bipolar disorder likelihood of ECT did not differ from depression. A higher number of mental health outpatient visits in the prior year and an involuntary index admission with depression were also associated with receiving ECT. Likelihood of receiving ECT increased with year of admission (HR = 1.32), private patient status (HR = 2.06), higher socioeconomic status (HR = 1.09) and being married (HR = 1.25). Conclusions: ECT use for depression and bipolar disorder in NSW aligns with clinical national guidelines. Patients with schizophrenia/schizoaffective, schizophrenia-related disorders, mania and other mood disorders had lower likelihood of ECT than depression, despite ECT being recommended by clinical guidelines for these diagnoses. Variations in ECT were strongly associated with healthcare access, with private patients twice as likely to receive ECT than their public counterparts, suggesting a need to explore ECT accessibility. [ABSTRACT FROM AUTHOR]

Background: The global aging population raises concerns about increased neurodegenerative diseases, particularly in low‐ and middle‐income countries like Latin America and the Caribbean. However, the situation among the indigenous inhabitants remains unknown due to various barriers, including cultural diversity, lack of studies, low awareness, language barriers, and limited healthcare access. Brief cognitive tests like the Rowland Universal Dementia Assessment Scale (RUDAS) show promise in overcoming these challenges. Method: A secondary analysis was conducted on a substantial patient cohort derived from the GAPP study (NIA grant #alz093273AG069118), categorizing participants based on whether their native language was Spanish or Quechua/Aymara. Descriptive analysis of variables was performed, with the Wilcoxon test applied to compare total RUDAS scores among distinct patient groups, including controls, individuals with Mild Cognitive Impairment (MCI), and those with dementia. Comparisons were specifically made between Spanish speakers and native language speakers. Additionally, the ROC (Receiver Operating Characteristic) curve was employed to evaluate the discriminative capacity of RUDAS in distinguishing between controls and dementia, as well as between controls/MCI and dementia cases within native and Spanish‐speaking populations. Result: A total of 405 controls, 126 individuals with Mild Cognitive Impairment (MCI), and 133 participants with dementia were included in the analysis. Among them, 91 patients were native language speakers, with a median age of 74 (range 54 ‐ 92). The majority were female (69.2%), and 65.9% were Aymara speakers. Native participants reported an average education level of 3.1 years (SD 4.4). The RUDAS mean score was lower in the native speaker group compared to Spanish‐speaking participants (21 vs. 23). Additionally, the analysis revealed significantly lower scores in controls within the native speaker group (Fig. 1). Diagnostic performance for native speakers was poor when comparing control/MCI (Fig. 2) vs. dementia and control vs. dementia (Fig. 3). Conclusion: The use of the RUDAS in native language speakers and its ability to distinguish between Mild Cognitive Impairment (MCI) and dementia raise some concerns. To improve assessments for various communities in Latin America and the Caribbean, there is a need for culturally adapted brief cognitive tests. [ABSTRACT FROM AUTHOR]