Background: Health services researchers spend a substantial amount of time performing integration, cleansing, interpretation, and aggregation of raw data from multiple public or private data sources. Often, each researcher (or someone in their team) duplicates this effort for their own project, facing the same challenges and experiencing the same pitfalls discovered by those before them. Objective: This paper described a design process for creating a data warehouse that includes the most frequently used databases in health services research. Methods: The design is based on a conceptual iterative process model framework that utilizes the sociotechnical systems theory approach and includes the capacity for subsequent updates of the existing data sources and the addition of new ones. We introduce the theory and the framework and then explain how they are used to inform the methodology of this study. Results: The application of the iterative process model to the design research process of problem identification and solution design for the Healthcare Research and Analytics Data Infrastructure Solution (HRADIS) is described. Each phase of the iterative model produced end products to inform the implementation of HRADIS. The analysis phase produced the problem statement and requirements documents. The projection phase produced a list of tasks and goals for the ideal system. Finally, the synthesis phase provided the process for a plan to implement HRADIS. HRADIS structures and integrates data dictionaries provided by the data sources, allowing the creation of dimensions and measures for a multidimensional business intelligence system. We discuss how HRADIS is complemented with a set of data mining, analytics, and visualization tools to enable researchers to more efficiently apply multiple methods to a given research project. HRADIS also includes a built-in security and account management framework for data governance purposes to ensure customized authorization depending on user roles and parts of the data the roles are authorized to access. Conclusions: To address existing inefficiencies during the obtaining, extracting, preprocessing, cleansing, and filtering stages of data processing in health services research, we envision HRADIS as a full-service data warehouse integrating frequently used data sources, processes, and methods along with a variety of data analytics and visualization tools. This paper presents the application of the iterative process model to build such a solution. It also includes a discussion on several prominent issues, lessons learned, reflections and recommendations, and future considerations, as this model was applied.

In recent years, because of the advancements in communication and networking technologies, mobile technologies have been developing at an unprecedented rate. mHealth, the use of mobile technologies in medicine, and the related research has also surged parallel to these technological advancements. Although there have been several attempts to review mHealth research through manual processes such as systematic reviews, the sheer magnitude of the number of studies published in recent years makes this task very challenging. The most recent developments in machine learning and text mining offer some potential solutions to address this challenge by allowing analyses of large volumes of texts through semi-automated processes. The objective of this study is to analyze the evolution of mHealth research by utilizing text-mining and natural language processing (NLP) analyses. The study sample included abstracts of 5,644 mHealth research articles, which were gathered from five academic search engines by using search terms such as mobile health, and mHealth. The analysis used the Text Explorer module of JMP Pro 13 and an iterative semi-automated process involving tokenizing, phrasing, and terming. After developing the document term matrix (DTM) analyses such as single value decomposition (SVD), topic, and hierarchical document clustering were performed, along with the topic-informed document clustering approach. The results were presented in the form of word-clouds and trend analyses. There were several major findings regarding research clusters and trends. First, our results confirmed time-dependent nature of terminology use in mHealth research. For example, in earlier versus recent years the use of terminology changed from “mobile phone” to “smartphone” and from “applications” to “apps”. Second, ten clusters for mHealth research were identified including (I) Clinical Research on Lifestyle Management, (II) Community Health, (III) Literature Review, (IV) Medical Interventions, (V) Research Design, (VI) Infrastructure, (VII) Applications, (VIII) Research and Innovation in Health Technologies, (IX) Sensor-based Devices and Measurement Algorithms, (X) Survey-based Research. Third, the trend analyses indicated the infrastructure cluster as the highest percentage researched area until 2014. The Research and Innovation in Health Technologies cluster experienced the largest increase in numbers of publications in recent years, especially after 2014. This study is unique because it is the only known study utilizing text-mining analyses to reveal the streams and trends for mHealth research. The fast growth in mobile technologies is expected to lead to higher numbers of studies focusing on mHealth and its implications for various healthcare outcomes. Findings of this study can be utilized by researchers in identifying areas for future studies.

Aim To examine associations between retinal thickness and rod-mediated dark adaptation in older adults with non-exudative age-related maculopathy (ARM) or normal macular health. Methods A cross-sectional study was conducted with 74 adults ≥50 years old from the comprehensive ophthalmology and retina services of an academic eye centre. ARM presence and disease severity in the enrolment eye was defined by the masked grading of stereofundus photos using the Clinical Age-Related Maculopathy grading system. High-definition, spectral-domain optical coherence tomography was used to estimate retinal thickness in a grid of regions in the macula. Rod-mediated dark adaptation, recovery of light sensitivity after a photo-bleach, was measured over a 20-min period for a 500 nm target presented at 5° on the inferior vertical meridian. Main outcomes of interest were retinal thickness in the macula (μm) and parameters of rod-mediated dark adaptation (second slope, third slope, average sensitivity, final sensitivity). Results In non-exudative disease retinal thickness was decreased in greater disease severity; thinner retina was associated with reductions in average and final rod-mediated sensitivity even after adjustment for age and visual acuity. Conclusions Impairment in rod-mediated dark adaptation in non-exudative ARM is associated with macular thinning.

Background: Emergency department (ED) overcrowding remains a critical challenge, leading to delays in patient care and increased operational strain. Current hospital management strategies often rely on reactive decision-making, addressing congestion only after it occurs. However, effective patient flow management requires early identification of overcrowding risks to allow timely interventions. Machine learning (ML)–based predictive modeling offers a solution by forecasting key patient flow measures, such as waiting count, enabling proactive resource allocation and improved hospital efficiency. Objective: The aim of this study is to develop ML models that predict ED waiting room occupancy (waiting count) at 2 temporal resolutions. The first approach is the hourly prediction model, which estimates the waiting count exactly 6 hours ahead at each prediction time (eg, a 1 PM prediction forecasts 7 PM). The second approach is the daily prediction model, which forecasts the average waiting count for the next 24-hour period (eg, a 5 PM prediction estimates the following day’s average). These predictive tools support resource allocation and help mitigate overcrowding by enabling proactive interventions before congestion occurs. Methods: Data from a partner hospital’s ED in the southeastern United States were used, integrating internal and external sources. Eleven different ML algorithms, ranging from traditional approaches to deep learning architectures, were systematically trained and evaluated on both hourly and daily predictions to determine the models that achieved the lowest prediction error. Experiments optimized feature combinations, and the best models were tested under high patient volume and across different hours to assess temporal accuracy. Results: The best hourly prediction performance was achieved by time series vision transformer plus (TSiTPlus) with a mean absolute error (MAE) of 4.19 and a mean squared error (MSE) of 29.36. The overall hourly waiting count had a mean of 18.11 and a SD (σ) of 9.77. Prediction accuracy varied by time of day, with the lowest MAE at 11 PM (2.45) and the highest at 8 PM (5.45). Extreme case analysis at (mean + 1σ), (mean + 2σ), and (mean + 3σ) resulted in MAEs of 6.16, 10.16, and 15.59, respectively. For daily predictions, an explainable convolutional neural network plus (XCMPlus) achieved the best results with an MAE of 2.00 and a MSE of 6.64. The daily waiting count had a mean of 18.11 and a SD of 4.51. Both models outperformed traditional forecasting approaches across multiple evaluation metrics. Conclusions: The proposed prediction models effectively forecast ED waiting count at both hourly and daily intervals. The results demonstrate the value of integrating diverse data sources and applying advanced modeling techniques to support proactive resource allocation decisions. The implementation of these forecasting tools within hospital management systems has the potential to improve patient flow and reduce overcrowding in emergency care settings. The code is available in our GitHub repository.

The objectives of this study were to evaluate sexual dimorphism for facial features within Colombian and Mexican-American populations and to compare the facial morphology by sex between these 2 populations. Three-dimensional facial images were acquired by using the portable 3dMDface system, which captured 223 subjects from 2 population groups of Colombians (n = 131) and Mexican-Americans (n = 92). Each population was categorized into male and female groups for evaluation. All subjects in the groups were aged between 18 and 30 years and had no apparent facial anomalies. A total of 21 anthropometric landmarks were identified on the 3-dimensional faces of each subject. The independent t test was used to analyze each data set obtained within each subgroup. The Colombian males showed significantly greater width of the outercanthal width, eye fissure length, and orbitale than the Colombian females. The Colombian females had significantly smaller lip and mouth measurements for all distances except upper vermillion height than Colombian males. The Mexican-American females had significantly smaller measurements with regard to the nose than Mexican-American males. Meanwhile, the heights of the face, the upper face, the lower face, and the mandible were all significantly less in the Mexican-American females. The intercanthal and outercanthal widths were significantly greater in the Mexican-American males and females. Meanwhile, the orbitale distance of Mexican-American sexes was significantly smaller than those of the Colombian males and females. The Mexican-American group had significantly larger nose width and length of alare than the Colombian group regarding both sexes. With respect to the nasal tip protrusion and nose height, they were significantly smaller in the Colombian females than in the Mexican-American females. The face width was significantly greater in the Colombian males and females. Sexual dimorphism for facial features was presented in both the Colombian and Mexican-American populations. In addition, there were significant differences in facial morphology between these 2 populations.