PLOS digital health最新文献

Immigrants and refugees seeking admission to the United States must first undergo an overseas medical exam, overseen by the US Centers for Disease Control and Prevention (CDC), during which all persons ≥15 years old receive a chest x-ray to look for signs of tuberculosis. Although individual screening sites often implement quality control (QC) programs to ensure radiographs are interpreted correctly, the CDC does not currently have a method for conducting similar QC reviews at scale. We obtained digitized chest radiographs collected as part of the overseas immigration medical exam. Using radiographs from applicants 15 years old and older, we trained deep learning models to perform three tasks: identifying abnormal radiographs; identifying abnormal radiographs suggestive of tuberculosis; and identifying the specific findings (e.g., cavities or infiltrates) in abnormal radiographs. We then evaluated the models on both internal and external testing datasets, focusing on two classes of performance metrics: individual-level metrics, like sensitivity and specificity, and sample-level metrics, like accuracy in predicting the prevalence of abnormal radiographs. A total of 152,012 images (one image per applicant; mean applicant age 39 years) were used for model training. On our internal test dataset, our models performed well both in identifying abnormalities suggestive of TB (area under the curve [AUC] of 0.97; 95% confidence interval [CI]: 0.95, 0.98) and in estimating sample-level counts of the same (-2% absolute percentage error; 95% CIC: -8%, 6%). On the external test datasets, our models performed similarly well in identifying both generic abnormalities (AUCs ranging from 0.89 to 0.92) and those suggestive of TB (AUCs from 0.94 to 0.99). This performance was consistent across metrics, including those based on thresholded class predictions, like sensitivity, specificity, and F1 score. Strong performance relative to high-quality radiological reference standards across a variety of datasets suggests our models may make reliable tools for supporting chest radiography QC activities at CDC.

Disparities in pulse oximetry accuracy, disproportionately affecting patients of color, have been associated with serious clinical outcomes. Although many have called for pulse oximetry hardware replacement, the cost associated with this replacement is not known. The objective of this study was to estimate the cost of replacing all current pulse oximetry hardware throughout a hospital system via a single-center survey in 2023 at an academic medical center (Duke University) with three hospitals. The main outcome was the cost of total hardware replacement as identified by current day prices for hardware. New and used prices for 3,542/4,136 (85.6%) across three hospitals for pulse oximetry devices were found. The average cost to replace current pulse oximetry hardware is $6,834.61 per bed. Replacement and integration costs are estimated at $14.2-17.4 million for the entire medical system. Extrapolating these costs to 5,564 hospitals in the United States results in an estimated cost of $8.72 billion. "Simply replacing" current pulse oximetry hardware to address disparities may not be simple, cheap, or timely. Solutions for addressing pulse oximetry accuracy disparities leveraging current technology may be necessary, and might also be better. Trial Registration: Pro00113724, exempt.

Groundbreaking data-sharing techniques and quick access to stored research data from the African continent are highly beneficial to create diverse unbiased datasets to inform digital health technologies and artificial intelligence in healthcare. Yet health researchers in sub-Saharan Africa (SSA) experience individual and collective challenges that render them cautious and even hesitant to share data despite acknowledging the public health benefits of sharing. This qualitative study reports on the perspectives of health researchers regarding strategies to mitigate these challenges. In-depth interviews were conducted via Microsoft Teams with 16 researchers from 16 different countries across SSA between July 2022 and April 2023. Purposive and snowball sampling techniques were used to invite participants via email. Recorded interviews were transcribed, cleaned, coded and managed through Atlas.ti.22. Thematic Analysis was used to analyse the data. Three recurrent themes and several subthemes emerged around strategies to improve governance of data sharing. The main themes identified were (1) Strategies for change at a policy level: guideline development, (2) Strengthening data governance to improve data quality and (3) Reciprocity: towards equitable data sharing. Building trust is central to the promotion of data sharing amongst researchers on the African continent and with global partners. This can be achieved by enhancing research integrity and strengthening micro and macro level governance. Substantial resources are required from funders and governments to enhance data governance practices, to improve data literacy and to enhance data quality. High quality data from Africa will afford diversity to global data sets, reducing bias in algorithms built for artificial intelligence technologies in healthcare. Engagement with multiple stakeholders including researchers and research communities is necessary to establish an equitable data sharing approach based on reciprocity and mutual benefit.

Return visit admissions (RVA), which are instances where patients discharged from the emergency department (ED) rapidly return and require hospital admission, have been associated with quality issues and adverse outcomes. We developed and validated a machine learning model to predict 72-hour RVA using electronic health records (EHR) data. Study data were extracted from EHR data in 2019 from three urban EDs. The development and independent validation datasets included 62,154 patients from two EDs and 73,453 patients from one ED, respectively. Multiple machine learning algorithms were evaluated, including deep significance clustering (DICE), regularized logistic regression (LR), Gradient Boosting Decision Tree, and XGBoost. These machine learning models were also compared against an existing clinical risk score. To support clinical actionability, clinician investigators conducted manual chart reviews of the cases identified by the model. Chart reviews categorized predicted cases across index ED discharge diagnosis and RVA root cause classifications. The best-performing model achieved an AUC of 0.87 in the development site (test set) and 0.75 in the independent validation set. The model, which combined DICE and LR, boosted predictive performance while providing well-defined features. The model was relatively robust to sensitivity analyses regarding performance across age, race, and by varying predictor availability but less robust across diagnostic groups. Clinician examination demonstrated discrete model performance characteristics within clinical subtypes of RVA. This machine learning model demonstrated a strong predictive performance for 72- RVA. Despite the limited clinical actionability potentially due to model complexity, the rarity of the outcome, and variable relevance, the clinical examination offered guidance on further variable inclusion for enhanced predictive accuracy and actionability.

Research on digital health equity has developed in important ways especially since the onset of the COVID-19 pandemic, with a series of clear recommendations now established for policy and practice. However, research and policy addressing the health system dimensions of digital health equity is needed to examine the appropriate roles of digital technologies in enabling access to care. We use a highly cited framework by Levesque et al on patient-centered access to care and the World Health Organization's framework on digitally enabled health systems to generate insights into the ways that digital solutions can support access to needed health care for structurally marginalized communities. Specifically, we mapped the frameworks to identify where applications of digital health do and do not support access to care, documenting which dimensions of access are under-addressed by digital health. Our analysis suggests that digital health has disproportionately focused on downstream enablers of access to care, which are low-yield when equity is the goal. We identify important opportunities for policy makers, funders and other stakeholders to attend more to digital solutions that support upstream enablement of peoples' abilities to understand, perceive, and seek out care. These areas are an important focal point for digital interventions and have the potential to be more equity-enhancing than downstream interventions at the time that care is accessed. Overall, we highlight the importance of taking a health system perspective when considering the roles of digital technologies in enhancing or inhibiting equitable access to needed health care.

Problem gambling is a major public health concern and is associated with profound psychological distress and economic problems. There are numerous gambling communities on the internet where users exchange information about games, gambling tactics, as well as gambling-related problems. Individuals exhibiting higher levels of problem gambling engage more in such communities. Online gambling communities may provide insights into problem-gambling behaviour. Using data scraped from a major German gambling discussion board, we fine-tuned a large language model, specifically a Bidirectional Encoder Representations from Transformers (BERT) model, to predict signs of problem-gambling from forum posts. Training data were generated by manual annotation and by taking into account diagnostic criteria and gambling-related cognitive distortions. Using cross-validation, our models achieved a precision of 0.95 and F1 score of 0.71, demonstrating that satisfactory classification performance can be achieved by generating high-quality training material through manual annotation based on diagnostic criteria. The current study confirms that a BERT-based model can be reliably used on small data sets and to detect signatures of problem gambling in online communication data. Such computational approaches may have potential for the detection of changes in problem-gambling prevalence among online users.

Given the suboptimal performance of Boolean searching to identify methodologically sound and clinically relevant studies in large bibliographic databases, exploring machine learning (ML) to efficiently classify studies is warranted. To boost the efficiency of a literature surveillance program, we used a large internationally recognized dataset of articles tagged for methodological rigor and applied an automated ML approach to train and test binary classification models to predict the probability of clinical research articles being of high methodologic quality. We trained over 12,000 models on a dataset of titles and abstracts of 97,805 articles indexed in PubMed from 2012-2018 which were manually appraised for rigor by highly trained research associates and rated for clinical relevancy by practicing clinicians. As the dataset is unbalanced, with more articles that do not meet the criteria for rigor, we used the unbalanced dataset and over- and under-sampled datasets. Models that maintained sensitivity for high rigor at 99% and maximized specificity were selected and tested in a retrospective set of 30,424 articles from 2020 and validated prospectively in a blinded study of 5253 articles. The final selected algorithm, combining a LightGBM (gradient boosting machine) model trained in each dataset, maintained high sensitivity and achieved 57% specificity in the retrospective validation test and 53% in the prospective study. The number of articles needed to read to find one that met appraisal criteria was 3.68 (95% CI 3.52 to 3.85) in the prospective study, compared with 4.63 (95% CI 4.50 to 4.77) when relying only on Boolean searching. Gradient-boosting ML models reduced the work required to classify high quality clinical research studies by 45%, improving the efficiency of literature surveillance and subsequent dissemination to clinicians and other evidence users.

In recent years, there has been substantial work in low-cost medical diagnostics based on the physical manifestations of disease. This is due to advancements in data analysis techniques and classification algorithms and the increased availability of computing power through smart devices. Smartphones and their ability to interface with simple sensors such as inertial measurement units (IMUs), microphones, piezoelectric sensors, etc., or with convenient attachments such as lenses have revolutionized the ability collect medically relevant data easily. Even if the data has relatively low resolution or signal to noise ratio, newer algorithms have made it possible to identify disease with this data. Many low-cost diagnostic tools have been created in medical fields spanning from neurology to dermatology to obstetrics. These tools are particularly useful in low-resource areas where access to expensive diagnostic equipment may not be possible. The ultimate goal would be the creation of a "diagnostic toolkit" consisting of a smartphone and a set of sensors and attachments that can be used to screen for a wide set of diseases in a community healthcare setting. However, there are a few concerns that still need to be overcome in low-cost diagnostics: lack of incentives to bring these devices to market, algorithmic bias, "black box" nature of the algorithms, and data storage/transfer concerns.