DIGITAL HEALTH最新文献

[This corrects the article DOI: 10.1177/20552076241258455.].

Background: Digital health has been widely used in delivering healthcare, presenting emerging opportunities to overcome barriers to effective obesity care. One strategy suggested for addressing obesity involves a hybrid weight management intervention that incorporates digital health. This scoping review aimed to map existing evidence regarding hybrid weight management intervention.

Methods: PubMed, Scopus, Cochrane Library, and the Web of Science electronic databases were searched for studies published between January 1, 2012 and May 16, 2023, with language restricted to English. The focus was on controlled trials in which a hybrid weight management intervention was used in the intervention among overweight or obese adults. The scoping review framework followed Arksey and O'Malley's guidelines and the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Protocols (PRISM-P).

Results: Full-text article review in the screening stage resulted in a total of 10 articles being included for narrative synthesis. Almost two-third of the articles originated from the United States (60%), followed by Europe and Australia, each accounting for 20%. The most common hybrid weight management intervention type was the combination of face-to-face and telehealth (i.e. phone call/text messaging) (40%), closely followed by a combination email intervention (30%) and mHealth apps intervention (30%). Most of the face-to-face dietary interventions were delivered as a group counseling (80%), while some were conducted as individual counseling (20%). Most studies observed a positive effect of the hybrid weight management intervention on body weight (weight lost 3.9-8.2 kg), body mass index (decreased 0.58 kg/m²), waist circumference (decreased 2.25 cm), and physical activity level compared to standard care. Findings suggest a direct association between hybrid weight management interventions and weight loss. The weight loss ranged from 3.9 to 8.2 kg, with some evidence indicating a significant weight loss of 5% from baseline. There is a need to explore stakeholders' telehealth perspective to optimize the delivery of hybrid weight management interventions, thereby maximizing greatest benefits for weight management.

Objective: Diabetes is a metabolic disorder that causes the risk of stroke, heart disease, kidney failure, and other long-term complications because diabetes generates excess sugar in the blood. Machine learning (ML) models can aid in diagnosing diabetes at the primary stage. So, we need an efficient ML model to diagnose diabetes accurately.

Methods: In this paper, an effective data preprocessing pipeline has been implemented to process the data and random oversampling to balance the data, handling the imbalance distributions of the observational data more sophisticatedly. We used four different diabetes datasets to conduct our experiments. Several ML algorithms were used to determine the best models to predict diabetes faultlessly.

Results: The performance analysis demonstrates that among all ML algorithms, random forest surpasses the current works with an accuracy rate of 86% and 98.48% for Dataset 1 and Dataset 2; extreme gradient boosting and decision tree surpass with an accuracy rate of 99.27% and 100% for Dataset 3 and Dataset 4, respectively. Our proposal can increase accuracy by 12.15% compared to the model without preprocessing.

Conclusions: This excellent research finding indicates that the proposed models might be employed to produce more accurate diabetes predictions to supplement current preventative interventions to reduce the incidence of diabetes and its associated costs.

Objective: Lifestyle intervention can produce clinically significant weight loss and reduced disease risk/severity for many individuals with overweight/obesity. Dietary lapses, instances of non-adherence to the recommended dietary goal(s) in lifestyle intervention, are associated with less weight loss and higher energy intake. There are distinct "types" of dietary lapse (e.g., eating an off-plan food, eating a larger portion), and behavioral, psychosocial, and contextual mechanisms may differ across dietary lapse types. Some lapse types also appear to impact weight more than others. Elucidating clear lapse types thus has potential for understanding and improving adherence to lifestyle intervention.

Methods: This 18-month observational cohort study will use real-time digital assessment tools within a multi-level factor analysis framework to uncover "lapse phenotypes" and understand their impact on clinical outcomes. Adults with overweight/obesity (n = 150) will participate in a 12-month online lifestyle intervention and 6-month weight loss maintenance period. Participants will complete 14-day lapse phenotyping assessment periods at baseline, 3, 6, 12, and 18 months in which smartphone surveys, wearable devices, and geolocation will assess dietary lapses and relevant phenotyping characteristics. Energy intake (via 24-h dietary recall) and weight will be collected at each assessment period.

Results: This trial is ongoing; data collection began on 31 October 2022 and is scheduled to complete by February 2027.

Conclusion: Results will inform novel precision tools to improve dietary adherence in lifestyle intervention, and support updated theoretical models of adherence behavior. Additionally, these phenotyping methods can likely be leveraged to better understand non-adherence to other health behavior interventions.

Trial registration: This study was prospectively registered https://clinicaltrials.gov/study/NCT05562427.

Background: Household air pollution (HAP) is a leading environmental risk factor accounting for about 1.6 million premature deaths mainly in low- and middle-income countries (LMICs). However, no multicounty randomized controlled trials have assessed the effect of liquefied petroleum gas (LPG) stove intervention on HAP and maternal and child health outcomes. The Household Air Pollution Intervention Network (HAPIN) was the first to assess this by implementing a common protocol in four LMICs.

Objective: This manuscript describes the implementation of the HAPIN data management protocol via Research Electronic Data Capture (REDCap) used to collect over 50 million data points in more than 4000 variables from 80 case report forms (CRFs).

Methods: We recruited 800 pregnant women in each study country (Guatemala, India, Peru, and Rwanda) who used biomass fuels in their households. Households were randomly assigned to receive LPG stoves and 18 months of free LPG supply (intervention) or to continue using biomass fuels (control). Households were followed for 18 months and assessed for primary health outcomes: low birth weight, severe pneumonia, and stunting. The HAPIN Data Management Core (DMC) implemented identical REDCap projects for each study site using shared variable names and timelines in local languages. Field staff collected data offline using tablets on the REDCap Mobile Application.

Results: Utilizing the REDCap application allowed the HAPIN DMC to collect and store data securely, access data (near real-time), create reports, perform quality control, update questionnaires, and provide timely feedback to local data management teams. Additional REDCap functionalities (e.g. scheduling, data validation, and barcode scanning) supported the study.

Conclusions: While the HAPIN trial experienced some challenges, REDCap effectively met HAPIN study goals, including quality data collection and timely reporting and analysis on this important global health trial, and supported more than 40 peer-reviewed scientific publications to date.

Objective: The presence of a lightweight convolutional neural network (CNN) model with a high-accuracy rate and low complexity can be useful in building an early obesity detection system, especially on mobile-based applications. The previous works of the CNN model for obesity detection were focused on the accuracy performances without considering the complexity size. In this study, we aim to build a new lightweight CNN model that can accurately classify normal and obese thermograms with low complexity sizes.

Methods: The DenseNet201 CNN architectures were modified by replacing the standard convolution layers with multiple depthwise and pointwise convolution layers from the MobileNet architectures. Then, the depth network of the dense block was reduced to determine which depths were the most comparable to obtain minimum validation losses. The proposed model then was compared with state-of-the-art DenseNet and MobileNet CNN models in terms of classification performances, and complexity size, which is measured in model size and computation cost.

Results: The results of the testing experiment show that the proposed model has achieved an accuracy of 81.54% with a model size of 1.44 megabyte (MB). This accuracy was comparable to that of DenseNet, which was 83.08%. However, DenseNet's model size was 71.77 MB. On the other hand, the proposed model's accuracy was higher than that of MobileNetV2, which was 79.23%, with a computation cost of 0.69 billion floating-point operations per second (GFLOPS), which approximated that of MobileNetV2, which was 0.59 GFLOPS.

Conclusions: The proposed model inherited the feature-extracting ability from the DenseNet201 architecture while keeping the lightweight complexity characteristic of the MobileNet architecture.

Objective: The modern era of cognitive intelligence in clinical space has led to the rise of 'Medical Cognitive Virtual Agents' (MCVAs) which are labeled as intelligent virtual assistants interacting with users in a context-sensitive and ambient manner. They aim to augment users' cognitive capabilities thereby helping both patients and medical experts in providing personalized healthcare like remote health tracking, emergency healthcare and robotic diagnosis of critical illness, among others. The objective of this study is to explore the technical aspects of MCVA and their relevance in modern healthcare.

Methods: In this study, a comprehensive and interpretable analysis of MCVAs are presented and their impacts are discussed. A novel system framework prototype based on artificial intelligence for MCVA is presented. Architectural workflow of potential applications of functionalities of MCVAs are detailed. A novel MCVA relevance survey analysis was undertaken during March-April 2023 at Bhubaneswar, Odisha, India to understand the current position of MCVA in society.

Results: Outcome of the survey delivered constructive results. Majority of people associated with healthcare showed their inclination towards MCVA. The curiosity for MCVA in Urban zone was more than in rural areas. Also, elderly citizens preferred using MCVA more as compared to youths. Medical decision support emerged as the most preferred application of MCVA.

Conclusion: The article established and validated the relevance of MCVA in modern healthcare. The study showed that MCVA is likely to grow in future and can prove to be an effective assistance to medical experts in coming days.

Objective: Aortic dissection (AD) is a severe emergency with high morbidity and mortality, necessitating strict monitoring and management. This retrospective study aimed to identify prognostic factors and establish predictive models for in-hospital mortality among AD patients in the intensive care unit (ICU).

Methods: We retrieved ICU admission records of AD patients from the Medical Information Mart for Intensive Care (MIMIC)-IV critical care data set and the eICU Collaborative Research Database. Functional data analysis was further applied to estimate continuous vital sign processes, and variables associated with in-hospital mortality were identified through univariate analyses. Subsequently, we employed multivariable logistic regression and machine learning techniques, including simple decision tree, random forest (RF), and eXtreme Gradient Boosting (XGBoost) to develop prognostic models for in-hospital mortality.

Results: Given 643 ICU admissions from MIMIC-IV and 501 admissions from eICU, 29 and 28 prognostic factors were identified from each database through univariate analyses, respectively. For prognostic model construction, 507 MIMIC-IV admissions were divided into 406 (80%) for training and 101 (20%) for internal validation, and 87 eICU admissions were included as an external validation group. Of the four models tested, the RF consistently exhibited the best performance among different variable subsets, boasting area under the receiver operating characteristic curves of 0.870 and 0.850. The models highlighted the mean 24-h fluid intake as the most potent prognostic factor.

Conclusions: The current prognostic models effectively forecasted in-hospital mortality among AD patients, and they pinpointed noteworthy prognostic factors, including initial blood pressure upon ICU admission and mean 24-h fluid intake.

[This corrects the article DOI: 10.1177/20552076241232882.].

Objective: The COVID-19 outbreak compelled countries to take swift actions across various domains amidst substantial uncertainties. In Israel, significant COVID-19-related efforts were assigned to the Israeli Home Front Command (HFC). HFC faced the challenge of anticipating adequate resources to efficiently and timely manage its numerous assignments despite the absence of a COVID-19 spread forecast. This paper describes the initiative of a group of motivated, though nonexpert, people to provide the needed COVID-19 rate of spread of the epidemic forecasts.

Methods: To address this challenge, the Planning Chamber, reporting to the HFC Medical Commander, undertook the task of mapping HFC healthcare challenges and resource requirements. The nonexpert team continuously collected public COVID-19-related data published by the Israeli Ministry of Health (MoH) of verified cases, light cases, mild cases, serious condition cases, life-support cases, and deaths, and despite lacking expertise in statistics and healthcare and having no sophisticated statistical packages, generated forecasts using Microsoft^® Excel.

Results: The analysis methods and applications successfully demonstrated the desired outcome of the lockdown by showing a transition from exponential to polynomial growth in the spread of the virus. These forecasting activities enabled decision-makers to manage resources effectively, supporting the HFC's operations during the pandemic.

Conclusions: Nonexpert forecasting may become a necessity and be beneficial, and similar analysis efforts can be easily replicated in future events. However, they are inherently short-lived and should persist only until knowledge centers can bridge the expertise gap. It is crucial to identify major events, such as lockdowns, during forecasting due to their potential impact on spread rates. Despite the expertise gap, the Planning Chamber's approach provided valuable resource management insights for HFC's COVID-19 response.