JMIRx med最新文献

Background: Primary health care (PHC) is the backbone of universal health coverage, with community health workers (CHWs) being one of its critical pillars in lower-middle-income countries. Most CHW functions require them to be an efficient communicator, but their program development has been deficient in this area. Can IT provide some solutions? Moreover, can some IT-based CHW-delivered innovations help mothers and children in areas not covered by PHC services? We explored these questions during the development and feasibility testing of a digital application designed to improve the communication capacity of CHWs in two underserved areas of Islamabad.

Objective: This study aims to explore the perceptions, practices, and related gaps about mother and child health, and child development in an underserved area; develop and deploy a behavior change communication program to address the gaps; and assess the feasibility of the program.

Methods: We carried out a mixed methods study with three steps. First, we conducted 13 in-depth interviews and two focus group discussions with stakeholders to explore the issues faced by mothers living in these underserved areas. To address these barriers, we developed Sehat Ghar, a video-based health education application to demonstrate practices mothers and families needed to adopt. Second, we trained 10 volunteer CHWs from the same community to deliver health education using the application and assessed their pre-post knowledge and skills. Third, these CHWs visited pregnant and lactating mothers in the community with random observation of their work by a supporting supervisor.

Results: Initial exploration revealed a need for health-related knowledge among mothers and suboptimal utilization of public health care. Sehat Ghar used behavior change techniques, including knowledge transfer, enhancing mothers' self-efficacy, and improving family involvement in mother and child care. Volunteer CHWs were identified from the community, who after the training, showed a significant improvement in mean knowledge score (before: mean 8.00, SD 1.49; after: mean 11.40, SD 1.43; P<.001) about health. During supportive supervision, these CHWs were rated as excellent in their interaction with mothers and excellent or very good in using the application. The CHW and her community reported their satisfaction with the application and wanted its delivery regularly.

Conclusions: Sehat Ghar is a simple, easy-to-use digital application for CHWs and is acceptable to the community. Mothers appreciate the content and presentation and are ready to incorporate its messages into their daily practices. The real-world effectiveness of the innovation tested on 250 mother-infant pairs will be important for its proof of effectiveness. With its usefulness and adaptability, and the rapidly spreading use of mobile phones and internet technology, thi

Background: Brucellosis is both endemic and enzootic in Iraq, resulting in long-term morbidity for humans as well as economic loss. No previous study of the spatial and temporal patterns of brucellosis in Iraq was done to identify potential clustering of cases.

Objective: This study aims to detect the spatial and temporal distribution of human brucellosis in Iraq and identify any changes that occurred from 2007 to 2018.

Methods: A descriptive, cross-sectional study was conducted using secondary data from the Surveillance Section at the Communicable Diseases Control Center, Public Health Directorate, Ministry of Health in Iraq. The trends of cases by sex and age group from 2007 to 2018 were displayed. The seasonal distribution of the cases from 2007 to 2012 was graphed. We calculated the incidence of human brucellosis per district per year and used local Getis-Ord Gi* statistics to detect the spatial distribution of the data. The data were analyzed using Microsoft Excel and GeoDa software.

Results: A total of 51,508 human brucellosis cases were reported during the 12-year study period, with some missing data for age groups. Human brucellosis persisted annually in Iraq across the study period with no specific temporal clustering of cases. In contrast, spatial clustering was predominant in northern Iraq.

Conclusions: There were significant differences in the geographic distribution of brucellosis. The number of cases is the highest in the north and northeast regions of the country, which has borders with nearby countries. In addition, people in these areas depend more on locally made dairy products, which can be inadequately pasteurized. Despite the lack of significant temporal clustering of cases, the highest number of cases were reported during summer and spring. Considering these patterns when allocating resources to combat this disease, determining public health priorities, and planning prevention and control strategies is important.

Background: Information about the range of Hounsfield values for healthy teeth tissues could become an additional tool in assessing dental health and could be used, among other data, for subsequent machine learning.

Objective: The purpose of our study was to determine dental tissue densities in Hounsfield units (HU).

Methods: The total sample included 36 healthy children (n=21, 58% girls and n=15, 42% boys) aged 10-11 years at the time of the study. The densities of 320 teeth tissues were analyzed. Data were expressed as means and SDs. The significance was determined using the Student (1-tailed) t test. The statistical significance was set at P<.05.

Results: The densities of 320 teeth tissues were analyzed: 72 (22.5%) first permanent molars, 72 (22.5%) permanent central incisors, 27 (8.4%) second primary molars, 40 (12.5%) tooth germs of second premolars, 37 (11.6%) second premolars, 9 (2.8%) second permanent molars, and 63 (19.7%) tooth germs of second permanent molars. The analysis of the data showed that tissues of healthy teeth in children have different density ranges: enamel, from mean 2954.69 (SD 223.77) HU to mean 2071.00 (SD 222.86) HU; dentin, from mean 1899.23 (SD 145.94) HU to mean 1323.10 (SD 201.67) HU; and pulp, from mean 420.29 (SD 196.47) HU to mean 183.63 (SD 97.59) HU. The tissues (enamel and dentin) of permanent central incisors in the mandible and maxilla had the highest mean densities. No gender differences concerning the density of dental tissues were reliably identified.

Conclusions: The evaluation of Hounsfield values for dental tissues can be used as an objective method for assessing their densities. If the determined densities of the enamel, dentin, and pulp of the tooth do not correspond to the range of values for healthy tooth tissues, then it may indicate a pathology.

Background: The Society of Thoracic Surgeons and European System for Cardiac Operative Risk Evaluation (EuroSCORE) II risk scores are the most commonly used risk prediction models for in-hospital mortality after adult cardiac surgery. However, they are prone to miscalibration over time and poor generalization across data sets; thus, their use remains controversial. Despite increased interest, a gap in understanding the effect of data set drift on the performance of machine learning (ML) over time remains a barrier to its wider use in clinical practice. Data set drift occurs when an ML system underperforms because of a mismatch between the data it was developed from and the data on which it is deployed.

Objective: In this study, we analyzed the extent of performance drift using models built on a large UK cardiac surgery database. The objectives were to (1) rank and assess the extent of performance drift in cardiac surgery risk ML models over time and (2) investigate any potential influence of data set drift and variable importance drift on performance drift.

Methods: We conducted a retrospective analysis of prospectively, routinely gathered data on adult patients undergoing cardiac surgery in the United Kingdom between 2012 and 2019. We temporally split the data 70:30 into a training and validation set and a holdout set. Five novel ML mortality prediction models were developed and assessed, along with EuroSCORE II, for relationships between and within variable importance drift, performance drift, and actual data set drift. Performance was assessed using a consensus metric.

Results: A total of 227,087 adults underwent cardiac surgery during the study period, with a mortality rate of 2.76% (n=6258). There was strong evidence of a decrease in overall performance across all models (P<.0001). Extreme gradient boosting (clinical effectiveness metric [CEM] 0.728, 95% CI 0.728-0.729) and random forest (CEM 0.727, 95% CI 0.727-0.728) were the overall best-performing models, both temporally and nontemporally. EuroSCORE II performed the worst across all comparisons. Sharp changes in variable importance and data set drift from October to December 2017, from June to July 2018, and from December 2018 to February 2019 mirrored the effects of performance decrease across models.

Conclusions: All models show a decrease in at least 3 of the 5 individual metrics. CEM and variable importance drift detection demonstrate the limitation of logistic regression methods used for cardiac surgery risk prediction and the effects of data set drift. Future work will be required to determine the interplay between ML models and whether ensemble models could improve on their respective performance advantages.

Background: Our previous analysis showed how in-hospital mortality of intubated patients with COVID-19 in Greece is adversely affected by patient load and regional disparities.

Objective: We aimed to update this analysis to include the large Delta and Omicron waves that affected Greece during 2021-2022, while also considering the effect of vaccination on in-hospital mortality.

Methods: Anonymized surveillance data were analyzed from all patients with COVID-19 in Greece intubated between September 1, 2020, and April 4, 2022, and followed up until May 17, 2022. Time-split Poisson regression was used to estimate the hazard of dying as a function of fixed and time-varying covariates: the daily total count of intubated patients with COVID-19 in Greece, age, sex, COVID-19 vaccination status, region of the hospital (Attica, Thessaloniki, or rest of Greece), being in an intensive care unit, and an indicator for the period from September 1, 2021.

Results: A total of 14,011 intubated patients with COVID-19 were analyzed, of whom 10,466 (74.7%) died. Mortality was significantly higher with a load of 400-499 intubated patients, with an adjusted hazard ratio (HR) of 1.22 (95% CI 1.09-1.38), rising progressively up to 1.48 (95% CI 1.31-1.69) for a load of ≥800 patients. Hospitalization away from the Attica region was also independently associated with increased mortality (Thessaloniki: HR 1.22, 95% CI 1.13-1.32; rest of Greece: HR 1.64, 95% CI 1.54-1.75), as was hospitalization after September 1, 2021 (HR 1.21, 95% CI 1.09-1.36). COVID-19 vaccination did not affect the mortality of these already severely ill patients, the majority of whom (11,944/14,011, 85.2%) were unvaccinated.

Conclusions: Our results confirm that in-hospital mortality of severely ill patients with COVID-19 is adversely affected by high patient load and regional disparities, and point to a further significant deterioration after September 1, 2021, especially away from Attica and Thessaloniki. This highlights the need for urgent strengthening of health care services in Greece, ensuring equitable and high-quality care for all.

Background: In situations of acute stress, individuals may engage in prosocial behaviors or risk-taking self-oriented behaviors. The COVID-19 pandemic created large stress-promoting conditions that impacted individuals' decisions to adhere to COVID-19 preventative behaviors.

Objectives: The study aimed to examine the relationship between anxiety during the pandemic and adherence behaviors to prevent the spread of COVID-19, and the moderating influence of prosocial behaviors. We hypothesized that individuals with high anxiety during COVID-19 would adhere more to preventive COVID-19 behaviors than ones with low anxiety and that this relationship would be stronger in those individuals with higher prosocial behaviors.

Methods: A web-based survey was administered through the SONA web-based participant tool of the psychology department of a university in the Northeastern United States. A final sample of 54 undergraduate students completed web-based questionnaires during the second wave of the COVID-19 pandemic, from January to May 2021, which included demographic measures and surveys on prosocial behaviors, anxiety, and COVID-19 preventive behaviors. Moderation analyses were conducted using PROCESS in SPSS.

Results: Participants reported high levels of trait and state anxiety symptoms, most of them meeting or exceeding the cutoff criteria to be clinically meaningful (state anxiety: 47/54, 87%; trait anxiety: 38/44, 86%), and over 50% highly adhered to the COVID-19 preventive behaviors of wearing a face mask, using hand sanitizer, handwashing, coughing/sneezing into their elbow or a tissue, self-quarantining, maintaining social distance, avoiding social gatherings, and avoiding nonessential travel. No significant associations were observed between prosocial behavior, anxiety types, and adherence to COVID-19 preventive behaviors. However, when moderation analyses were conducted between anxiety types and adherence to COVID-19 preventive behaviors, results demonstrated a statistically significant interaction of public prosocial behavior with state anxiety (β=-.17, t53=-2.60; P=.01), predicting engagement in COVID-19 preventative behaviors. At high levels of anxiety, low levels of prosocial public behaviors were associated with higher engagement in COVID-19 preventative behaviors. In contrast, high levels of public prosocial behavior were associated with low engagement in COVID-19 preventative behaviors at higher levels of anxiety.

Conclusions: These results provide information that can aid in the creation of interventions that could increase adherence to COVID-19 preventative behaviors (Reviewed by the Plan P #PeerRef Community).

Background: Opioid and substance misuse has become a widespread problem in the United States, leading to the "opioid crisis." The relationship between substance misuse and mental health has been extensively studied, with one possible relationship being that substance misuse causes poor mental health. However, the lack of evidence on the relationship has resulted in opioids being largely inaccessible through legal means.

Objectives: This study aims to analyze social media posts related to substance use and opioids being sold through cryptomarket listings. The study aims to use state-of-the-art deep learning models to generate sentiment and emotion from social media posts to understand users' perceptions of social media. The study also aims to investigate questions such as which synthetic opioids people are optimistic, neutral, or negative about; what kind of drugs induced fear and sorrow; what kind of drugs people love or are thankful about; which drugs people think negatively about; and which opioids cause little to no sentimental reaction.

Methods: The study used the drug abuse ontology and state-of-the-art deep learning models, including knowledge-aware Bidirectional Encoder Representations From Transformers-based models, to generate sentiment and emotion from social media posts related to substance use and opioids being sold through cryptomarket listings. The study crawled cryptomarket data and extracted posts for fentanyl, fentanyl analogs, and other novel synthetic opioids. The study performed topic analysis associated with the generated sentiments and emotions to understand which topics correlate with people's responses to various drugs. Additionally, the study analyzed time-aware neural models built on these features while considering historical sentiment and emotional activity of posts related to a drug.

Results: The study found that the most effective model performed well (statistically significant, with a macro-F1-score of 82.12 and recall of 83.58) in identifying substance use disorder. The study also found that there were varying levels of sentiment and emotion associated with different synthetic opioids, with some drugs eliciting more positive or negative responses than others. The study identified topics that correlated with people's responses to various drugs, such as pain relief, addiction, and withdrawal symptoms.

Conclusions: The study provides insight into users' perceptions of synthetic opioids based on sentiment and emotion expressed in social media posts. The study's findings can be used to inform interventions and policies aimed at reducing substance misuse and addressing the opioid crisis. The study demonstrates the potential of deep learning models for analyzing social media data to gain insights into public health issues.