PLOS digital health最新文献

During pregnancy and early motherhood, the perinatal period, women use a variety of resources including digital resources to support social interactions, information seeking and health monitoring. While previous studies have investigated specific timepoints, this study takes a more holistic approach to understand how information needs and resources change over the perinatal period. Furthermore, we include the perspective of maternity healthcare professionals to better understand the relationship between different stakeholders in the information work of perinatal women. A total of 25 interviews with 10 UK based mothers and 5 healthcare professionals (3 Midwives and 2 Health visitors) were conducted. Perinatal women were asked about their information and support needs throughout pregnancy and the postnatal period, healthcare professionals were asked about information and support provision to perinatal women. Information work activities were grouped along stages of the perinatal timeline from pre-pregnancy to the postanal period to illustrate the work and perspectives of the women and the healthcare professionals. Information work varies considerably over the timeline of the perinatal period, shifting back and forth in focus between mother and baby. information work during this period consists of many information related activities including seeking, monitoring, recording, questioning, sharing and checking. The importance of the HCPs as stakeholders in this work is notable as is the digital support for information work. Importantly, paper-based resources are still an important shared resource allowing reflection and supporting communication. Information work for women varies across the perinatal timeline. Particular challenges exist at key transition points, and we suggest design considerations for more integrated digital resources that support information work focused on mother and baby to enhance communication between perinatal women and healthcare professionals.

Despite the emergence of antimicrobial-resistant (AMR) strains of Neisseria gonorrhoeae, the treatment of gonorrhea remains empiric and according to standardized guidelines, which are informed by the national prevalence of resistant strains. Yet, the prevalence of AMR varies substantially across geographic and demographic groups. We investigated whether data from the national surveillance system of AMR gonorrhea in the US could be used to personalize the empiric treatment of gonorrhea. We used data from the Gonococcal Isolate Surveillance Project collected between 2000-2010 to train and validate machine learning models to identify resistance to ciprofloxacin (CIP), one of the recommended first-line antibiotics until 2007. We used these models to personalize empiric treatments based on sexual behavior and geographic location and compared their performance with standardized guidelines, which recommended treatment with CIP, ceftriaxone (CRO), or cefixime (CFX) between 2005-2006, and either CRO or CFX between 2007-2010. Compared with standardized guidelines, the personalized treatments could have replaced 33% of CRO and CFX use with CIP while ensuring that 98% of patients were prescribed effective treatment during 2005-2010. The models maintained their performance over time and across geographic regions. Predictive models trained on data from national surveillance systems of AMR gonorrhea could be used to personalize the empiric treatment of gonorrhea based on patients' basic characteristics at the point of care. This approach could reduce the unnecessary use of newer antibiotics while maintaining the effectiveness of first-line therapy.

Postoperative delirium (POD) contributes to severe outcomes such as death or development of dementia. Thus, it is desirable to identify vulnerable patients in advance during the perioperative phase. Previous studies mainly investigated risk factors for delirium during hospitalization and further used a linear logistic regression (LR) approach with time-invariant data. Studies have not investigated patients' fluctuating conditions to support POD precautions. In this single-center study, we aimed to predict POD in a recovery room setting with a non-linear machine learning (ML) technique using pre-, intra-, and postoperative data. The target variable POD was defined with the Nursing Screening Delirium Scale (Nu-DESC) ≥ 1. Feature selection was conducted based on robust univariate test statistics and L1 regularization. Non-linear multi-layer perceptron (MLP) as well as tree-based models were trained and evaluated-with the receiver operating characteristics curve (AUROC), the area under precision recall curve (AUPRC), and additional metrics-against LR and published models on bootstrapped testing data. The prevalence of POD was 8.2% in a sample of 73,181 surgeries performed between 2017 and 2020. Significant univariate impact factors were the preoperative ASA status (American Society of Anesthesiologists physical status classification system), the intraoperative amount of given remifentanil, and the postoperative Aldrete score. The best model used pre-, intra-, and postoperative data. The non-linear boosted trees model achieved a mean AUROC of 0.854 and a mean AUPRC of 0.418 outperforming linear LR, well as best applied and retrained baseline models. Overall, non-linear machine learning models using data from multiple perioperative time phases were superior to traditional ones in predicting POD in the recovery room. Class imbalance was seen as a main impediment for model application in clinical practice.

Despite the widespread utilization of social media in HIV prevention interventions, little is known about the acceptance of social media in the dissemination of HIV prevention information among key at-risk groups like female sex workers (FSWs). This study has investigated FSWs' acceptance of Secret Facebook Group (SFG) in learning about HIV prevention. During June 2022, a quantitative study was conducted using a 5-star point Likert scale survey among 40 FSWs aged 18 years and older who took part in a Secret Facebook Group (SFG) HIV intervention. Descriptive statistics described demographics, social media accessibility, perceived usefulness (PU), perceived ease of use (PEOU), and acceptance among survey participants using SPSS and SAS. Most study participants found SFG utilized in HIV prevention intervention acceptable. Seventy-five percent (75%) of participants selected 5 stars for the acceptance of SFG. The majority of participants used social media, spent more than 90 minutes on social media per day, and could participate in the SFG HIV prevention intervention if airtime was not provided by study investigators, despite experiencing times when the internet was interrupted. The results also showed the PU and PEOU mean scores of SFG in the HIV prevention intervention were slightly lower than the acceptance scores (4.70 and 4.50 vs. 4.74). The data suggested future research should focus on explaining FSWs acceptance of social media and identifying social media platform alternatives for HIV prevention intervention. This study provided useful insights into social media acceptance, use, and importance in HIV prevention education among FSWs. The findings also indicate the need for further research on the reasons for acceptance of social media and relevant social media platforms supporting HIV prevention education among FSWs.

Background and objectives: A key step in electrocardiogram (ECG) analysis is the detection of QRS complexes, particularly for arrhythmia detection. Telehealth ECGs present a new challenge for automated analysis as they are noisier than traditional clinical ECGs. The aim of this study was to identify the best-performing open-source QRS detector for use with telehealth ECGs.

Methods: The performance of 18 open-source QRS detectors was assessed on six datasets. These included four datasets of ECGs collected under supervision, and two datasets of telehealth ECGs collected without clinical supervision. The telehealth ECGs, consisting of single-lead ECGs recorded between the hands, included a novel dataset of 479 ECGs collected in the SAFER study of screening for atrial fibrillation (AF). Performance was assessed against manual annotations.

Results: A total of 12 QRS detectors performed well on ECGs collected under clinical supervision (F1 score ≥0.96). However, fewer performed well on telehealth ECGs: five performed well on the TELE ECG Database; six performed well on high-quality SAFER data; and performance was poorer on low-quality SAFER data (three QRS detectors achieved F1 of 0.78-0.84). The presence of AF had little impact on performance.

Conclusions: The Neurokit and University of New South Wales QRS detectors performed best in this study. These performed sufficiently well on high-quality telehealth ECGs, but not on low-quality ECGs. This demonstrates the need to handle low-quality ECGs appropriately to ensure only ECGs which can be accurately analysed are used for clinical decision making.

Prediction of sepsis using machine-learning approaches has recently gained traction. However, the lack of translation of these algorithms into clinical routine remains a major issue. Existing early sepsis detection methods are either based on the older definition of sepsis or do not accurately detect sepsis leading to the high frequency of false-positive alarms. This results in a well-known issue of clinicians' "alarm fatigue", leading to decreased responsiveness and identification, ultimately resulting in delayed clinical intervention. Hence, there is a fundamental, unmet need for a clinical decision system capable of accurate and timely sepsis diagnosis, running at the point of need. In this work, SepsisAI-a deep-learning algorithm based on long short-term memory (LSTM) networks was developed to predict the early onset of hospital-acquired sepsis in real-time for patients admitted to the ICU. The models are trained and validated with data from the PhysioNet Challenge, consisting of 40,336 patient data files from two healthcare systems: Beth Israel Deaconess Medical Center and Emory University Hospital. In the short term, the algorithm tracks frequently measured vital signs, sparsely available lab parameters, demographic features, and certain derived features for making predictions. A real-time alert system, which monitors the trajectory of the predictions, is developed on top of the deep-learning framework to minimize false alarms. On a balanced test dataset, the model achieves an AUROC, AUPRC, sensitivity, and specificity of 0.95, 0.96, 88.19%, and 96.75%, respectively at the patient level. In terms of lookahead time, the model issues a warning at a median of 6 hours (IQR 6 to 20 hours) and raises an alert at a median of 4 hours (IQR 2 to 5 hours) ahead of sepsis onset. Most importantly, the model achieves a false-alarm ratio of 3.18% for alerts, which is significantly less than other sepsis alarm systems. Additionally, on a disease prevalence-based test set, the algorithm reported similar outcomes with AUROC and AUPRC of 0.94 and 0.87, respectively, with sensitivity, and specificity of 97.05%, and 96.75%, respectively. The proposed algorithm might serve as a clinical decision support system to assist clinicians in the accurate and timely diagnosis of sepsis. With exceptionally high specificity and low false-alarm rate, this algorithm also helps mitigate the well-known issue of clinician alert fatigue arising from currently proposed sepsis alarm systems. Consequently, the algorithm partially addresses the challenges of successfully integrating machine-learning algorithms into routine clinical care.

Introduction: Diagnosis is a key step towards the provision of medical intervention and saving lives. However, in low- and middle-income countries, diagnostic services are mainly centralized in large cities and are costly. Point of care (POC) diagnostic technologies have been developed to fill the diagnostic gap for remote areas. The linkage of POC testing onto smartphones has leveraged the ever-expanding coverage of mobile phones to enhance health services in low- and middle-income countries. Tanzania, like most other middle-income countries, is poised to adopt and deploy the use of mobile phone-enabled diagnostic devices. However, there is limited information on the situation on the ground with regard to readiness and capabilities of the veterinary and medical professionals to make use of this technology.

Methods: In this study we survey awareness, digital literacy and prevalent health condition to focus on in Tanzania to guide development and future implementation of mobile phoned-enable diagnostic tools by veterinary and medical professionals. Data was collected using semi-structured questionnaire with closed and open-ended questions, guided in-depth interviews and focus group discussion administered to the participants after informed consent was obtained.

Results: A total of 305 participants from six regions of Tanzania were recruited in the study. The distribution of participants across the six regions was as follows: Kilimanjaro (37), Arusha (31), Tabora (68), Dodoma (61), Mwanza (58), and Iringa (50). Our analysis reveals that only 48.2% (126/255) of participants demonstrated significant awareness of mobile phone-enabled diagnostics. This awareness varies significantly across age groups, professions and geographical locations. Interestingly, while 97.4% of participants own and can operate a smartphone, 62% have never utilized their smartphones for health services, including disease diagnosis. Regarding prevalent health condition to focus on when developing mobile phone -enabled diagnostics tools for Tanzania; there was disparity between medical and veterinary professionals. For medical professionals the top 4 priority diseases were Malaria, Urinary Tract Infections, HIV and Diabetes, while for veterinary professionals they were Brucellosis, Anthrax, Newcastle disease and Rabies.

Discussion: Despite the widespread ownership of smartphones among healthcare providers (both human and animal), only a small proportion have utilized these devices for healthcare practices, with none reported for diagnostic purposes. This limited utilization may be attributed to factors such as a lack of awareness, absence of policy guidelines, limited promotion, challenges related to mobile data connectivity, and adherence to cultural practices.

Conclusion: The majority of medical and veterinary professionals in Tanzania possess the necessary digital li

One of the most important tools available to limit the spread and impact of infectious diseases is vaccination. It is therefore important to understand what factors determine people's vaccination decisions. To this end, previous behavioural research made use of, (i) controlled but often abstract or hypothetical studies (e.g., vignettes) or, (ii) realistic but typically less flexible studies that make it difficult to understand individual decision processes (e.g., clinical trials). Combining the best of these approaches, we propose integrating real-world Bluetooth contacts via smartphones in several rounds of a game scenario, as a novel methodology to study vaccination decisions and disease spread. In our 12-week proof-of-concept study conducted with N = 494 students, we found that participants strongly responded to some of the information provided to them during or after each decision round, particularly those related to their individual health outcomes. In contrast, information related to others' decisions and outcomes (e.g., the number of vaccinated or infected individuals) appeared to be less important. We discuss the potential of this novel method and point to fruitful areas for future research.

To improve clinical diagnoses, assessments of potential cardiac disease risk, and predictions of lethal arrhythmias, the analysis of electrocardiograms (ECGs) requires a more accurate method of weighting waveforms to efficiently detect abnormalities that appear as minute strains in the waveforms. In addition, the inverse problem of estimating the myocardial action potential from the ECG has been a longstanding challenge. To analyze the variance of the ECG waveforms and to estimate collective myocardial action potentials (APs) from the ECG, we designed a model equation incorporating the probability densities of Gaussian functions of time-series point processes in the cardiac cycle and dipoles of the collective APs in the myocardium. The equation, which involves taking the difference between the cumulative distribution functions (CDFs) that represent positive endocardial and negative epicardial potentials, fits both R and T waves. The mean, standard deviation, weights, and level of each cumulative distribution function (CDF) are metrics for the variance of the transition state of the collective myocardial AP. Clinical ECGs of myocardial ischemia during coronary intervention show abnormalities in the aforementioned specific elements of the tensor associated with repolarization transition variance earlier than in conventional indicators of ischemia. The tensor can be used to evaluate the beat-to-beat dynamic repolarization changes between the ventricular epi and endocardium in terms of the Mahalanobis distance (MD). This tensor-based cardiography that uses the differences between CDFs to show changes in collective myocardial APs has the potential to be a new analysis tool for ECGs.

Artificial Intelligence (AI) has been increasingly integrated into healthcare settings, including the radiology department to aid radiographic image interpretation, including reporting by radiographers. Trust has been cited as a barrier to effective clinical implementation of AI. Appropriating trust will be important in the future with AI to ensure the ethical use of these systems for the benefit of the patient, clinician and health services. Means of explainable AI, such as heatmaps have been proposed to increase AI transparency and trust by elucidating which parts of image the AI 'focussed on' when making its decision. The aim of this novel study was to quantify the impact of different forms of AI feedback on the expert clinicians' trust. Whilst this study was conducted in the UK, it has potential international application and impact for AI interface design, either globally or in countries with similar cultural and/or economic status to the UK. A convolutional neural network was built for this study; trained, validated and tested on a publicly available dataset of MUsculoskeletal RAdiographs (MURA), with binary diagnoses and Gradient Class Activation Maps (GradCAM) as outputs. Reporting radiographers (n = 12) were recruited to this study from all four regions of the UK. Qualtrics was used to present each participant with a total of 18 complete examinations from the MURA test dataset (each examination contained more than one radiographic image). Participants were presented with the images first, images with heatmaps next and finally an AI binary diagnosis in a sequential order. Perception of trust in the AI systems was obtained following the presentation of each heatmap and binary feedback. The participants were asked to indicate whether they would change their mind (or decision switch) in response to the AI feedback. Participants disagreed with the AI heatmaps for the abnormal examinations 45.8% of the time and agreed with binary feedback on 86.7% of examinations (26/30 presentations).'Only two participants indicated that they would decision switch in response to all AI feedback (GradCAM and binary) (0.7%, n = 2) across all datasets. 22.2% (n = 32) of participants agreed with the localisation of pathology on the heatmap. The level of agreement with the GradCAM and binary diagnosis was found to be correlated with trust (GradCAM:-.515;-.584, significant large negative correlation at 0.01 level (p = < .01 and-.309;-.369, significant medium negative correlation at .01 level (p = < .01) for GradCAM and binary diagnosis respectively). This study shows that the extent of agreement with both AI binary diagnosis and heatmap is correlated with trust in AI for the participants in this study, where greater agreement with the form of AI feedback is associated with greater trust in AI, in particular in the heatmap form of AI feedback. Forms of explainable AI should be developed with cognisance of the need for precision and accuracy in localisation to p