A Mobile Health Behavior Change Intervention for Women With Coronary Heart Disease: A RANDOMIZED CONTROLLED PILOT STUDY.

PURPOSE: The aim of this study was to evaluate the effects of a mobile health (mHealth) intervention, HerBeat, compared with educational usual care (E-UC) for improving exercise capacity (EC) and other patient-reported outcomes at 3 mo among women with coronary heart disease. METHODS: Women were randomized to the HerBeat group (n = 23), a behavior change mHealth intervention with a smartphone, smartwatch, and health coach or to the E-UC group (n = 24) who received a standardized cardiac rehabilitation workbook. The primary endpoint was EC measured with the 6-min walk test (6MWT). Secondary outcomes included cardiovascular disease risk factors and psychosocial well-being. RESULTS: A total of 47 women (age 61.2 ± 9.1 yr) underwent randomization. The HerBeat group significantly improved on the 6MWT from baseline to 3 mo ( P = .016, d = .558) while the E-UC group did not ( P = .894, d =-0.030). The between-group difference of 38 m at 3 mo was not statistically significant. From baseline to 3 mo, the HerBeat group improved in anxiety ( P = .021), eating habits confidence ( P = .028), self-efficacy for managing chronic disease ( P = .001), diastolic blood pressure ( P = .03), general health perceptions ( P = .047), perceived bodily pain ( P = .02), and waist circumference ( P = .008) while the E-UC group showed no improvement on any outcomes. CONCLUSIONS: The mHealth intervention led to improvements in EC and several secondary outcomes from baseline to 3 mo while the E-UC intervention did not. A larger study is required to detect small differences between groups. The implementation and outcomes evaluation of the HerBeat intervention was feasible and acceptable with minimal attrition.

Classifying stages in the gonotrophic cycle of mosquitoes from images using computer vision techniques.

The ability to distinguish between the abdominal conditions of adult female mosquitoes has important utility for the surveillance and control of mosquito-borne diseases. However, doing so requires entomological training and time-consuming manual effort. Here, we design computer vision techniques to determine stages in the gonotrophic cycle of female mosquitoes from images. Our dataset was collected from 139 adult female mosquitoes across three medically important species-Aedes aegypti, Anopheles stephensi, and Culex quinquefasciatus-and all four gonotrophic stages of the cycle (unfed, fully fed, semi-gravid, and gravid). From these mosquitoes and stages, a total of 1959 images were captured on a plain background via multiple smartphones. Subsequently, we trained four distinct AI model architectures (ResNet50, MobileNetV2, EfficientNet-B0, and ConvNeXtTiny), validated them using unseen data, and compared their overall classification accuracies. Additionally, we analyzed t-SNE plots to visualize the formation of decision boundaries in a lower-dimensional space. Notably, ResNet50 and EfficientNet-B0 demonstrated outstanding performance with an overall accuracy of 97.44% and 93.59%, respectively. EfficientNet-B0 demonstrated the best overall performance considering computational efficiency, model size, training speed, and t-SNE decision boundaries. We also assessed the explainability of this EfficientNet-B0 model, by implementing Grad-CAMs-a technique that highlights pixels in an image that were prioritized for classification. We observed that the highest weight was for those pixels representing the mosquito abdomen, demonstrating that our AI model has indeed learned correctly. Our work has significant practical impact. First, image datasets for gonotrophic stages of mosquitoes are not yet available. Second, our algorithms can be integrated with existing citizen science platforms that enable the public to record and upload biological observations. With such integration, our algorithms will enable the public to contribute to mosquito surveillance and gonotrophic stage identification. Finally, we are aware of work today that uses computer vision techniques for automated mosquito species identification, and our algorithms in this paper can augment these efforts by enabling the automated detection of gonotrophic stages of mosquitoes as well.

Citizen Science as an Approach for Responding to the Threat of Anopheles stephensi in Africa.

Even as novel technologies emerge and medicines advance, pathogen-transmitting mosquitoes pose a deadly and accelerating public health threat. Detecting and mitigating the spread of Anopheles stephensi in Africa is now critical to the fight against malaria, as this invasive mosquito poses urgent and unprecedented risks to the continent. Unlike typical African vectors of malaria, An. stephensi breeds in both natural and artificial water reservoirs, and flourishes in urban environments. With An. stephensi beginning to take hold in heavily populated settings, citizen science surveillance supported by novel artificial intelligence (AI) technologies may offer impactful opportunities to guide public health decisions and community-based interventions. Coalitions like the Global Mosquito Alert Consortium (GMAC) and our freely available digital products can be incorporated into enhanced surveillance of An. stephensi and other vector-borne public health threats. By connecting local citizen science networks with global databases that are findable, accessible, interoperable, and reusable (FAIR), we are leveraging a powerful suite of tools and infrastructure for the early detection of, and rapid response to, (re)emerging vectors and diseases.

Artificial intelligence versus natural selection: Using computer vision techniques to classify bees and bee mimics.

Many groups of stingless insects have independently evolved mimicry of bees to fool would-be predators. To investigate this mimicry, we trained artificial intelligence (AI) algorithms-specifically, computer vision-to classify citizen scientist images of bees, bumble bees, and diverse bee mimics. For detecting bees and bumble bees, our models achieved accuracies of 91.71 % and 88.86 % , respectively. As a proxy for a natural predator, our models were poorest in detecting bee mimics that exhibit both aggressive and defensive mimicry. Using the explainable AI method of class activation maps, we validated that our models learn from appropriate components within the image, which in turn provided anatomical insights. Our t-SNE plot yielded perfect within-group clustering, as well as between-group clustering that grossly replicated the phylogeny. Ultimately, the transdisciplinary approaches herein can enhance global citizen science efforts as well as investigations of mimicry and morphology of bees and other insects.

Integrating Global Citizen Science Platforms to Enable Next-Generation Surveillance of Invasive and Vector Mosquitoes.

Mosquito-borne diseases continue to ravage humankind with >700 million infections and nearly one million deaths every year. Yet only a small percentage of the >3500 mosquito species transmit diseases, necessitating both extensive surveillance and precise identification. Unfortunately, such efforts are costly, time-consuming, and require entomological expertise. As envisioned by the Global Mosquito Alert Consortium, citizen science can provide a scalable solution. However, disparate data standards across existing platforms have thus far precluded truly global integration. Here, utilizing Open Geospatial Consortium standards, we harmonized four data streams from three established mobile apps­Mosquito Alert, iNaturalist, and GLOBE Observer's Mosquito Habitat Mapper and Land Cover­to facilitate interoperability and utility for researchers, mosquito control personnel, and policymakers. We also launched coordinated media campaigns that generated unprecedented numbers and types of observations, including successfully capturing the first images of targeted invasive and vector species. Additionally, we leveraged pooled image data to develop a toolset of artificial intelligence algorithms for future deployment in taxonomic and anatomical identification. Ultimately, by harnessing the combined powers of citizen science and artificial intelligence, we establish a next-generation surveillance framework to serve as a united front to combat the ongoing threat of mosquito-borne diseases worldwide.

Evaluation of bactericidal effects of silver hydrosol nanotherapeutics against Enterococcus faecium 1449 drug resistant biofilms.

Introduction: Silver (Ag) nanoparticles (NPs) are well documented for their broad-spectrum bactericidal effects. This study aimed to test the effect of bioactive Ag-hydrosol NPs on drug-resistant E. faecium 1449 strain and explore the use of artificial intelligence (AI) for automated detection of the bacteria. Methods: The formation of E. faecium 1449 biofilms in the absence and presence of Ag-hydrosol NPs at different concentrations ranging from 12.4 mg/L to 123 mg/L was evaluated using a 3-dimentional culture system. The biofilm reduction was evaluated using the confocal microscopy in addition to the Transmission Electronic Microscopy (TEM) visualization and spectrofluorimetric quantification using a Biotek Synergy Neo2 microplate reader. The cytotoxicity of the NPs was evaluated in human nasal epithelial cells using the MTT assay. The AI technique based on Fast Regional Convolutional Neural Network architecture was used for the automated detection of the bacteria. Results: Treatment with Ag-hydrosol NPs at concentrations ranging from 12.4 mg/L to 123 mg/L resulted in 78.09% to 95.20% of biofilm reduction. No statistically significant difference in biofilm reduction was found among different batches of Ag-hydrosol NPs. Quantitative concentration-response relationship analysis indicated that Ag-hydrosol NPs exhibited a relative high anti-biofilm activity and low cytotoxicity with an average EC50 and TC50 values of 0.0333 and 6.55 mg/L, respectively, yielding an average therapeutic index value of 197. The AI-assisted TEM image analysis allowed automated detection of E. faecium 1449 with 97% ~ 99% accuracy. Discussion: Conclusively, the bioactive Ag-hydrosol NP is a promising nanotherapeutic agent against drug-resistant pathogens. The AI-assisted TEM image analysis was developed with the potential to assess its treatment effect.

A framework based on deep neural networks to extract anatomy of mosquitoes from images.

We design a framework based on Mask Region-based Convolutional Neural Network to automatically detect and separately extract anatomical components of mosquitoes-thorax, wings, abdomen and legs from images. Our training dataset consisted of 1500 smartphone images of nine mosquito species trapped in Florida. In the proposed technique, the first step is to detect anatomical components within a mosquito image. Then, we localize and classify the extracted anatomical components, while simultaneously adding a branch in the neural network architecture to segment pixels containing only the anatomical components. Evaluation results are favorable. To evaluate generality, we test our architecture trained only with mosquito images on bumblebee images. We again reveal favorable results, particularly in extracting wings. Our techniques in this paper have practical applications in public health, taxonomy and citizen-science efforts.

A Mobile Health Intervention System for Women With Coronary Heart Disease: Usability Study.

BACKGROUND: Coronary heart disease (CHD) is the leading cause of death and disability among American women. The prevalence of CHD is expected to increase by more than 40% by 2035. In 2015, the estimated cost of caring for patients with CHD was US $182 billion in the United States; hospitalizations accounted for more than half of the costs. Compared with men, women with CHD or those who have undergone coronary revascularization have up to 30% more rehospitalizations within 30 days and up to 1 year. Center-based cardiac rehabilitation is the gold standard of care after an acute coronary event, but few women attend these valuable programs. Effective home-based interventions for improving cardiovascular health among women with CHD are vital for addressing this gap in care. OBJECTIVE: The ubiquity of mobile phones has made mobile health (mHealth) behavioral interventions a viable option to improve healthy behaviors of both women and men with CHD. First, this study aimed to examine the usability of a prototypic mHealth intervention designed specifically for women with CHD (herein referred to as HerBeat). Second, we examined the influence of HerBeat on selected health behaviors (self-efficacy for diet, exercise, and managing chronic illness) and psychological (perceived stress and depressive symptoms) characteristics of the participants. METHODS: Using a single-group, pretest, posttest design, 10 women participated in the 12-week usability study. Participants were provided a smartphone and a smartwatch on which the HerBeat app was installed. Using a web portal dashboard, a health coach monitored participants' ecological momentary assessment data, their behavioral data, and their heart rate and step count. Participants then completed a 12-week follow-up assessment. RESULTS: All 10 women (age: mean 64.4 years, SD 6.3 years) completed the study. The usability and acceptability of HerBeat were good, with a mean system usability score of 83.60 (SD 16.3). The participants demonstrated statistically significant improvements in waist circumference (P=.048), weight (P=.02), and BMI (P=.01). Furthermore, depressive symptoms, measured with the Patient Health Questionnaire-9, significantly improved from baseline (P=.04). CONCLUSIONS: The mHealth prototype was feasible and usable for women with CHD. Participants provided data that were useful for further development of HerBeat. The mHealth intervention is expected to help women with CHD self-manage their health behaviors. A randomized controlled trial is needed to further verify the findings.

TussisWatch: A Smart-Phone System to Identify Cough Episodes as Early Symptoms of Chronic Obstructive Pulmonary Disease and Congestive Heart Failure.

Chronic obstructive pulmonary disease (COPD) and congestive heart failure (CHF) are leading chronic health concerns among the aging population today. They are both typically characterized by episodes of cough that share similarities. In this paper, we design TussisWatch, a smart-phone-based system to record and process cough episodes for early identification of COPD or CHF. In our technique, for each cough episode, we do the following: 1) filter noise; 2) use domain expertise to partition each cough episode into multiple segments, indicative of disease or otherwise; 3) identify a limited number of audio features for each cough segment; 4) remove inherent biases as a result of sample size differences; and 5) design a two-level classification scheme, based on the idea of Random Forests, to process a recorded cough segment. Our classifier, at the first-level, identifies whether or not a given cough segment indicates a disease. If yes, the second-level classifier identifies the cough segment as symptomatic of COPD or CHF. Testing with a cohort of 9 COPD, 9 CHF, and 18 CONTROLS subjects spread across both the genders, races, and ages, our system achieves good performance in terms of Sensitivity, Specificity, Accuracy, and Area under ROC curve. The proposed system has the potential to aid early access to healthcare, and may be also used to educate patients on self-care at home.

Watch-Dog: Detecting Self-Harming Activities From Wrist Worn Accelerometers.

In a 2012 survey, in the United States alone, there were more than 35 000 reported suicides with approximately 1800 of being psychiatric inpatients. Recent Centers for Disease Control and Prevention (CDC) reports indicate an upward trend in these numbers. In psychiatric facilities, staff perform intermittent or continuous observation of patients manually in order to prevent such tragedies, but studies show that they are insufficient, and also consume staff time and resources. In this paper, we present the Watch-Dog system, to address the problem of detecting self-harming activities when attempted by in-patients in clinical settings. Watch-Dog comprises of three key components-Data sensed by tiny accelerometer sensors worn on wrists of subjects; an efficient algorithm to classify whether a user is active versus dormant (i.e., performing a physical activity versus not performing any activity); and a novel decision selection algorithm based on random forests and continuity indices for fine grained activity classification. With data acquired from 11 subjects performing a series of activities (both self-harming and otherwise), Watch-Dog achieves a classification accuracy of , , and for same-user 10-fold cross-validation, cross-user 10-fold cross-validation, and cross-user leave-one-out evaluation, respectively. We believe that the problem addressed in this paper is practical, important, and timely. We also believe that our proposed system is practically deployable, and related discussions are provided in this paper.