Hasil untuk "Computer applications to medicine. Medical informatics"

Alexander MacLellan, Keisuke Takano

Abstract BackgroundHikikomori is a state of social withdrawal first identified in Japan and is gaining interest globally. Classically, hikikomori is described as a state of isolation within one’s home, though recent conceptualizations have proposed a continuum of severity. Hikikomori frequently shares symptoms with depression, social anxiety, autism, and schizophrenia, as well as internet and gaming disorders. Clinical case studies and cross-sectional studies suggest that dysfunctional emotion regulation, familial support, and internet behaviors are proposed to contribute to the onset and maintenance of a withdrawn state, though they have not been explored longitudinally. ObjectiveThis study aims to investigate affective, behavioral, and cognitive correlates of hikikomori symptoms, and how daily mood, social enjoyment, familial support, and internet usage may maintain a socially withdrawn state. MethodsA minimum of 84 participants aged between 18 and 60 years will complete self-report measures of hikikomori symptoms, internet addiction, depression, anxiety, autism, and fear of offending others before participating in 14 days of ecological momentary assessment surveys. Surveys will be delivered 5 times per day from 8 AM to 10 PM, measuring mood, internet behavior, familial relationships, social interaction frequency, anticipatory and consummatory enjoyment, sleep quality, and physical activity. Participants will repeat the self-report measure of hikikomori symptoms postmonitoring period. ResultsRecruitment began in November 21, 2025. Data collection and analysis are scheduled to be completed by summer 2026, with the results also scheduled to be available by the end of summer 2026. Correlation and multiple regression analyses will investigate whether internet addiction, social anxiety, expressive suppression, fear of offending others, daily mood, internet use, social enjoyment, and familial support predict hikikomori symptoms. Time-lagged network analyses will explore the temporal dynamics of these relationships, and how these differ in those with high and low levels of hikikomori symptoms. Finally, time-lagged logistic regressions will explore which factors predict future social behavior. ConclusionsThis study will be the first to investigate currently proposed mechanisms underlying hikikomori, while also exploring the time-varying relationships between affect and social behavior. The results will provide initial evidence for factors that predict hikikomori symptoms, explore candidate mechanisms underlying hikikomori, and identify potential maintenance factors as targets for intervention.

Mengying Zhang, Lawrence Doi, Maria Wolters et al.

The worldwide tobacco epidemic continues to present significant public health challenges, necessitating persistent smoking cessation efforts. Mobile applications have shown potential as effective tools to aid individuals in quitting smoking, yet there is limited understanding of how it works. This study utilised a realist evaluation approach to establish programme theories that explain how smoking cessation applications help Chinese smokers stop smoking.

Simon Wallraf, Sara Köthemann, Claudia Wiesemann et al.

BackgroundPatient organizations (POs) are an integral part of the health care landscape, serving as advocates and support systems for patients and their families. As the digitalization of health care accelerates, POs are challenged to adapt their diverse roles to digital formats. However, the extent and form of POs’ digital adaptation and the challenges POs encounter in their digital transformation remain unexplored. ObjectiveThis study aims to investigate the digital transformation processes within POs. We examined the types of digital activities and processes implemented, people involved in respective tasks, challenges encountered, and attitudes toward the digitalization of POs. MethodsThe study was carried out by the multicenter interdisciplinary research network Pandora. We adopted a qualitative exploratory approach by conducting 37 semistructured interviews and 2 focus groups with representatives and members of POs in Germany. Results were obtained using a deductive-inductive approach based on a qualitative content analysis. Methods and results were reported in accordance with the COREQ (Consolidated Criteria for Reporting Qualitative Research) checklist. ResultsPOs primarily apply basic digital tools to engage in communication, health education, and information dissemination. Some also develop specific mobile apps and collect health data through patient registries. Volunteers cover a considerable part of the workload. Sometimes, POs collaborate with external partners, such as health professionals or other nonprofit organizations. Furthermore, many (13/46, 28%) interviewees referred to the importance of involving members in digitalization efforts to better meet their needs. However, they described the actual practices used to involve members in, for example, developing digital services as limited, passive, or implicit. When evaluating digital transformation processes, representatives and members of POs expressed generally positive attitudes and acknowledged their potential to improve the accessibility of support services, management efficiency, and outreach. Still, resource constraints; the complexity of digital initiatives; and accessibility issues for certain demographic groups, especially older persons, were frequently mentioned as challenges. Several (15/46, 33%) interviewees highlighted POs’ increasing responsibility to support their members’ digital competencies and digital health literacy. ConclusionsPOs are actively involved in the digital transformation of health services. To navigate challenges and further shape and sustain digital activities and processes, POs may benefit from governance frameworks, that is, a clear plan outlining with whom, how, and with what objectives digital projects are being realized. Support from public, scientific, and policy institutions to enhance the process through training, mentorship, and fostering collaborative networks seems warranted.

Tuong Minh Nguyen, Kim Leng Poh, Shu-Ling Chong et al.

Abstract Background Modeling patient data, particularly electronic health records (EHR), is one of the major focuses of machine learning studies in healthcare, as these records provide clinicians with valuable information that can potentially assist them in disease diagnosis and decision-making. Methods In this study, we present a multi-level graph-based framework called MedMGF, which models both patient medical profiles extracted from EHR data and their relationship network of health profiles in a single architecture. The medical profiles consist of several layers of data embedding derived from interval records obtained during hospitalization, and the patient-patient network is created by measuring the similarities between these profiles. We also propose a modification to the Focal Loss (FL) function to improve classification performance in imbalanced datasets without the need to imputate the data. MedMGF’s performance was evaluated against several Graphical Convolutional Network (GCN) baseline models implemented with Binary Cross Entropy (BCE), FL, class balancing parameter $$\alpha$$ α , and Synthetic Minority Oversampling Technique (SMOTE). Results Our proposed framework achieved high classification performance (AUC: 0.8098, ACC: 0.7503, SEN: 0.8750, SPE: 0.7445, NPV: 0.9923, PPV: 0.1367) on an extreme imbalanced pediatric sepsis dataset (n=3,014, imbalance ratio of 0.047). It yielded a classification improvement of 3.81% for AUC, 15% for SEN compared to the baseline GCN+ $$\alpha$$ α FL (AUC: 0.7717, ACC: 0.8144, SEN: 0.7250, SPE: 0.8185, PPV: 0.1559, NPV: 0.9847), and an improvement of 5.88% in AUC and 22.5% compared to GCN+FL+SMOTE (AUC: 0.7510, ACC: 0.8431, SEN: 0.6500, SPE: 0.8520, PPV: 0.1688, NPV: 0.9814). It also showed a classification improvement of 3.86% for AUC, 15% for SEN compared to the baseline GCN+ $$\alpha$$ α BCE (AUC: 0.7712, ACC: 0.8133, SEN: 0.7250, SPE: 0.8173, PPV: 0.1551, NPV: 0.9847), and an improvement of 14.33% in AUC and 27.5% in comparison to GCN+BCE+SMOTE (AUC: 0.6665, ACC: 0.7271, SEN: 0.6000, SPE: 0.7329, PPV: 0.0941, NPV: 0.9754). Conclusion When compared to all baseline models, MedMGF achieved the highest SEN and AUC results, demonstrating the potential for several healthcare applications.

Gioacchino D. De Sario Velasquez, MD, Sahar Borna, MD, Michael J. Maniaci, MD et al.

The objective of this study is to explore the current state of research concerning the cost-effectiveness of wearable health technologies, excluding hearing aids, owing to extensive previous investigation. A systematic review was performed using PubMed, EMBASE/MEDLINE, Google Scholar, and Cumulated Index to Nursing and Allied Health Literature to search studies evaluating the cost-effectiveness of wearable health devices in terms of quality-adjusted life years and incremental cost-effectiveness ratio. The search was conducted on March 28, 2023, and the date of publication did not limit the search. The search yielded 10 studies eligible for inclusion. These studies, published between 2012 and 2023, spanned various locations globally. The studies used data from hypothetical cohorts, existing research, randomized controlled trials, and meta-analyses. They covered a diverse range of wearable technologies applied in different health care settings, including respiratory rate monitors, pedometers, fall-prediction devices, hospital-acquired pressure injury prevention monitors, seizure detection devices, heart rate monitors, insulin therapy sensors, and wearable cardioverter defibrillators. The time horizons in the cost-effectiveness analyses ranged from less than a year to a lifetime. The studies indicate that wearable technologies can increase quality-adjusted life years and be cost-effective and potentially cost-saving. However, the cost-effectiveness depends on various factors, such as the type of device, the health condition being addressed, the specific perspective of the health economic analysis, local cost and payment structure, and willingness-to-pay thresholds. The use of wearables in health care promises improving outcomes and resource allocation. However, more research is needed to fully understand the long-term benefits and to strengthen the evidence base for health care providers, policymakers, and patients.

Nasim Aslani, Nasrin Galehdar, Ali Garavand

Seng Hansun, Ahmadreza Argha, Siaw-Teng Liaw et al.

BackgroundTuberculosis (TB) was the leading infectious cause of mortality globally prior to COVID-19 and chest radiography has an important role in the detection, and subsequent diagnosis, of patients with this disease. The conventional experts reading has substantial within- and between-observer variability, indicating poor reliability of human readers. Substantial efforts have been made in utilizing various artificial intelligence–based algorithms to address the limitations of human reading of chest radiographs for diagnosing TB. ObjectiveThis systematic literature review (SLR) aims to assess the performance of machine learning (ML) and deep learning (DL) in the detection of TB using chest radiography (chest x-ray [CXR]). MethodsIn conducting and reporting the SLR, we followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A total of 309 records were identified from Scopus, PubMed, and IEEE (Institute of Electrical and Electronics Engineers) databases. We independently screened, reviewed, and assessed all available records and included 47 studies that met the inclusion criteria in this SLR. We also performed the risk of bias assessment using Quality Assessment of Diagnostic Accuracy Studies version 2 (QUADAS-2) and meta-analysis of 10 included studies that provided confusion matrix results. ResultsVarious CXR data sets have been used in the included studies, with 2 of the most popular ones being Montgomery County (n=29) and Shenzhen (n=36) data sets. DL (n=34) was more commonly used than ML (n=7) in the included studies. Most studies used human radiologist’s report as the reference standard. Support vector machine (n=5), k-nearest neighbors (n=3), and random forest (n=2) were the most popular ML approaches. Meanwhile, convolutional neural networks were the most commonly used DL techniques, with the 4 most popular applications being ResNet-50 (n=11), VGG-16 (n=8), VGG-19 (n=7), and AlexNet (n=6). Four performance metrics were popularly used, namely, accuracy (n=35), area under the curve (AUC; n=34), sensitivity (n=27), and specificity (n=23). In terms of the performance results, ML showed higher accuracy (mean ~93.71%) and sensitivity (mean ~92.55%), while on average DL models achieved better AUC (mean ~92.12%) and specificity (mean ~91.54%). Based on data from 10 studies that provided confusion matrix results, we estimated the pooled sensitivity and specificity of ML and DL methods to be 0.9857 (95% CI 0.9477-1.00) and 0.9805 (95% CI 0.9255-1.00), respectively. From the risk of bias assessment, 17 studies were regarded as having unclear risks for the reference standard aspect and 6 studies were regarded as having unclear risks for the flow and timing aspect. Only 2 included studies had built applications based on the proposed solutions. ConclusionsFindings from this SLR confirm the high potential of both ML and DL for TB detection using CXR. Future studies need to pay a close attention on 2 aspects of risk of bias, namely, the reference standard and the flow and timing aspects. Trial RegistrationPROSPERO CRD42021277155; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=277155

Sok Ying Liaw, Jian Zhi Tan, Khairul Dzakirin Bin Rusli et al.

BackgroundInterprofessional communication is needed to enhance the early recognition and management of patients with sepsis. Preparing medical and nursing students using virtual reality simulation has been shown to be an effective learning approach for sepsis team training. However, its scalability is constrained by unequal cohort sizes between medical and nursing students. An artificial intelligence (AI) medical team member can be implemented in a virtual reality simulation to engage nursing students in sepsis team training. ObjectiveThis study aimed to evaluate the effectiveness of an AI-powered doctor versus a human-controlled doctor in training nursing students for sepsis care and interprofessional communication. MethodsA randomized controlled trial study was conducted with 64 nursing students who were randomly assigned to undertake sepsis team training with an AI-powered doctor (AI-powered group) or with medical students using virtual reality simulation (human-controlled group). Participants from both groups were tested on their sepsis and communication performance through simulation-based assessments (posttest). Participants’ sepsis knowledge and self-efficacy in interprofessional communication were also evaluated before and after the study interventions. ResultsA total of 32 nursing students from each group completed the simulation-based assessment, sepsis and communication knowledge test, and self-efficacy questionnaire. Compared with the baseline scores, both the AI-powered and human-controlled groups demonstrated significant improvements in communication knowledge (P=.001) and self-efficacy in interprofessional communication (P<.001) in posttest scores. For sepsis care knowledge, a significant improvement in sepsis care knowledge from the baseline was observed in the AI-powered group (P<.001) but not in the human-controlled group (P=.16). Although no significant differences were found in sepsis care performance between the groups (AI-powered group: mean 13.63, SD 4.23, vs human-controlled group: mean 12.75, SD 3.85, P=.39), the AI-powered group (mean 9.06, SD 1.78) had statistically significantly higher sepsis posttest knowledge scores (P=.009) than the human-controlled group (mean 7.75, SD 2.08). No significant differences were found in interprofessional communication performance between the 2 groups (AI-powered group: mean 29.34, SD 8.37, vs human-controlled group: mean 27.06, SD 5.69, P=.21). However, the human-controlled group (mean 69.6, SD 14.4) reported a significantly higher level of self-efficacy in interprofessional communication (P=.008) than the AI-powered group (mean 60.1, SD 13.3). ConclusionsOur study suggested that AI-powered doctors are not inferior to human-controlled virtual reality simulations with respect to sepsis care and interprofessional communication performance, which supports the viability of implementing AI-powered doctors to achieve scalability in sepsis team training. Our findings also suggested that future innovations should focus on the sociability of AI-powered doctors to enhance users’ interprofessional communication training. Perhaps in the nearer term, future studies should examine how to best blend AI-powered training with human-controlled virtual reality simulation to optimize clinical performance in sepsis care and interprofessional communication. Trial RegistrationClinicalTrials.gov NCT05953441; https://clinicaltrials.gov/study/NCT05953441

Chisato Imai, Janaki Amin, Mirela Prgomet et al.

Viacheslav V. Danilov, Alex Proutski, Alex Karpovsky et al.

The novel coronavirus 19 (COVID-19) continues to have a devastating effect around the globe, leading many scientists and clinicians to actively seek to develop new techniques to assist with the tackling of this disease. Modern machine learning methods have shown promise in their adoption to assist the healthcare industry through their data and analytics-driven decision making, inspiring researchers to develop new angles to fight the virus. In this paper, we aim to develop a CNN-based method for the detection of COVID-19 by utilizing patients' chest X-ray images. Developing upon the inclusion of convolutional units, the proposed method makes use of indirect supervision based on Grad-CAM. This technique is used in the training process where Grad-CAM's attention heatmaps support the network's predictions. Despite recent progress, scarcity of data has thus far limited the development of a robust solution. We extend upon existing work by combining publicly available data across 5 different sources and carefully annotate the comprising images across three categories: normal, pneumonia, and COVID-19. To achieve a high classification accuracy, we propose a training pipeline based on indirect supervision of traditional classification networks, where the guidance is directed by an external algorithm. With this method, we observed that the widely used, standard networks can achieve an accuracy comparable to tailor-made models, specifically for COVID-19, with one network in particular, VGG-16, outperforming the best of the tailor-made models.

Iain Cruickshank, Tamar Ginossar, Jason Sulskis et al.

BackgroundThe onset of the COVID-19 pandemic and the consequent “infodemic” increased concerns about Twitter’s role in advancing antivaccination messages, even before a vaccine became available to the public. New computational methods allow for analysis of cross-platform use by tracking links to websites shared over Twitter, which, in turn, can uncover some of the content and dynamics of information sources and agenda-setting processes. Such understanding can advance theory and efforts to reduce misinformation. ObjectiveInformed by agenda-setting theory, this study aimed to identify the content and temporal patterns of websites shared in vaccine-related tweets posted to COVID-19 conversations on Twitter between February and June 2020. MethodsWe used triangulation of data analysis methods. Data mining consisted of the screening of around 5 million tweets posted to COVID-19 conversations to identify tweets that related to vaccination and including links to websites shared within these tweets. We further analyzed the content the 20 most-shared external websites using a mixed methods approach. ResultsOf 841,896 vaccination-related tweets identified, 185,994 (22.1%) contained links to specific websites. A wide range of websites were shared, with the 20 most-tweeted websites constituting 14.5% (27,060/185,994) of the shared websites and typically being shared for only 2 to 3 days. Traditional media constituted the majority of these 20 websites, along with other social media and governmental sources. We identified markers of inauthentic propagation for some of these links. ConclusionsThe topic of vaccination was prevalent in tweets about COVID-19 early in the pandemic. Sharing websites was a common communication strategy, and its “bursty” pattern and inauthentic propagation strategies pose challenges for health promotion efforts. Future studies should consider cross-platform use in dissemination of health information and in counteracting misinformation.

Husnayain, Atina, Shim, Eunha, Fuad, Anis et al.

BackgroundSouth Korea is among the best-performing countries in tackling the coronavirus pandemic by using mass drive-through testing, face mask use, and extensive social distancing. However, understanding the patterns of risk perception could also facilitate effective risk communication to minimize the impacts of disease spread during this crisis. ObjectiveWe attempt to explore patterns of community health risk perceptions of COVID-19 in South Korea using internet search data. MethodsGoogle Trends (GT) and NAVER relative search volumes (RSVs) data were collected using COVID-19–related terms in the Korean language and were retrieved according to time, gender, age groups, types of device, and location. Online queries were compared to the number of daily new COVID-19 cases and tests reported in the Kaggle open-access data set for the time period of December 5, 2019, to May 31, 2020. Time-lag correlations calculated by Spearman rank correlation coefficients were employed to assess whether correlations between new COVID-19 cases and internet searches were affected by time. We also constructed a prediction model of new COVID-19 cases using the number of COVID-19 cases, tests, and GT and NAVER RSVs in lag periods (of 1-3 days). Single and multiple regressions were employed using backward elimination and a variance inflation factor of <5. ResultsThe numbers of COVID-19–related queries in South Korea increased during local events including local transmission, approval of coronavirus test kits, implementation of coronavirus drive-through tests, a face mask shortage, and a widespread campaign for social distancing as well as during international events such as the announcement of a Public Health Emergency of International Concern by the World Health Organization. Online queries were also stronger in women (r=0.763-0.823; P<.001) and age groups ≤29 years (r=0.726-0.821; P<.001), 30-44 years (r=0.701-0.826; P<.001), and ≥50 years (r=0.706-0.725; P<.001). In terms of spatial distribution, internet search data were higher in affected areas. Moreover, greater correlations were found in mobile searches (r=0.704-0.804; P<.001) compared to those of desktop searches (r=0.705-0.717; P<.001), indicating changing behaviors in searching for online health information during the outbreak. These varied internet searches related to COVID-19 represented community health risk perceptions. In addition, as a country with a high number of coronavirus tests, results showed that adults perceived coronavirus test–related information as being more important than disease-related knowledge. Meanwhile, younger, and older age groups had different perceptions. Moreover, NAVER RSVs can potentially be used for health risk perception assessments and disease predictions. Adding COVID-19–related searches provided by NAVER could increase the performance of the model compared to that of the COVID-19 case–based model and potentially be used to predict epidemic curves. ConclusionsThe use of both GT and NAVER RSVs to explore patterns of community health risk perceptions could be beneficial for targeting risk communication from several perspectives, including time, population characteristics, and location.

Kerry Wrighton-Araneda, Cristián Valdebenito, Gabriel Abarca et al.

This work contains data on the computational, structural, and electronic characterization of supported ionic liquids phases anchored to copper nanoparticles using Density Functional theory calculations. The data supplement the paper “Interaction of supported ionic liquids phases onto copper nanoparticles: A Density Functional Theory study” [1], based on the adsorption of ionic liquid onto a Cu nanoparticle is analyzed from a chemical and physical point of view. The chemical analysis is based on Atoms in Molecule theory (AIM) and allows us to differentiate the chemical binding nature between ionic liquid and copper nanoparticle. On the other hand, the energy decomposition analysis based on absolutely localized molecular orbital (ALMO-EDA) describes the physical contributions that govern the interaction between ionic liquid and the copper nanoparticles. Herein, detailed and extended information in the synthesis and computational characterization are presented.

Pierre Guy Atangana Njock, Shui-Long Shen, Annan Zhou et al.

The data presented in this paper pertain to case records of liquefaction potential surveys in earthquake prone areas. Field performances of 219 sites obtained from various regions (U.S.A, Japan, Turkey, China, Canada, etc …) are put on display. Specifically, this database consists of 253 cone penetration test (CPT) field records, among which 72 cases that did not liquefied and 181 cases that liquefied. In total, 10 principal variables are tabulated including the earthquake magnitude, maximum ground surface acceleration, depth, water depth, total overburden stress, effective overburden stress, Cone Penetration Test (CPT) tip resistance, CPT friction ratio, fines content, shear stress ratio. These data were arbitrarily split into a testing set of 53 cases and a training set of 200 cases. These field observations are compared to prediction values of liquefaction potential assessed using the evolutionary neural network proposed for “Evaluation of soil liquefaction with AI technology incorporating a coupled ENN/t-SNE model” [1]. Keywords: Liquefaction, Database, CPT, Neural network

Ishmael Festus Jaja, Chinwe Juliana Iwu

Foodborne pathogen such Salmonella enterica is a leading cause of human gastroenteritis worldwide. The potential to cause more severe and prolonged infection increases when the bacteria harbour resistant gene. In this dataset, S. enterica PCR confirmed isolates recovered from the formal (n = 33) and informal (n = 15) meat sector were further tested against 15 antimicrobials and 20 resistance determinants using the disc-diffusion method on Muller-Hinton agar and the genotypic antimicrobial resistance determinants by PCR. In addition, multiple antimicrobial resistance phenotype and the multiple antimicrobial resistance indexes were shown. The data suggest that meat from the formal sector harbour resistance capacity than meat from the informal sector. Keywords: Antimicrobial resistance, Meat, South Africa, Informal sector, Foodborne disease