Assessing the Readability of Online Patient Education Materials in Obstetrics and Gynecology Using Traditional Measures: Comparative Analysis and Limitations.

BACKGROUND: Patient education materials (PEMs) can be vital sources of information for the general population. However, despite American Medical Association (AMA) and National Institutes of Health (NIH) recommendations to make PEMs easier to read for patients with low health literacy, they often do not adhere to these recommendations. The readability of online PEMs in the obstetrics and gynecology (OB/GYN) field, in particular, has not been thoroughly investigated. OBJECTIVE: The study sampled online OB/GYN PEMs and aimed to examine (1) agreeability across traditional readability measures (TRMs), (2) adherence of online PEMs to AMA and NIH recommendations, and (3) whether the readability level of online PEMs varied by web-based source and medical topic. This study is not a scoping review, rather, it focused on scoring the readability of OB/GYN PEMs using the traditional measures to add empirical evidence to the literature. METHODS: A total of 1576 online OB/GYN PEMs were collected via 3 major search engines. In total 93 were excluded due to shorter content (less than 100 words), yielding 1483 PEMs for analysis. Each PEM was scored by 4 TRMs, including Flesch-Kincaid grade level, Gunning fog index, Simple Measure of Gobbledygook, and the Dale-Chall. The PEMs were categorized based on publication source and medical topic by 2 research team members. The readability scores of the categories were compared statistically. RESULTS: Results indicated that the 4 TRMs did not agree with each other, leading to the use of an averaged readability (composite) score for comparison. The composite scores across all online PEMs were not normally distributed and had a median at the 11th grade. Governmental PEMs were the easiest to read amongst source categorizations and PEMs about menstruation were the most difficult to read. However, the differences in the readability scores among the sources and the topics were small. CONCLUSIONS: This study found that online OB/GYN PEMs did not meet the AMA and NIH readability recommendations and would be difficult to read and comprehend for patients with low health literacy. Both findings connected well to the literature. This study highlights the need to improve the readability of OB/GYN PEMs to help patients make informed decisions. Research has been done to create more sophisticated readability measures for medical and health documents. Once validated, these tools need to be used by web-based content creators of health education materials.

Keep your distance! Measuring staff physical distancing during the Sars-Cov-2 pandemic using a real-time locating system.

INTRODUCTION: Staff-to-staff transmission of SARS-CoV-2 poses a significant risk to the Emergency Department (ED) workforce. We measured close (<6 ft), prolonged (>10 min) staff interactions in a busy pediatric Emergency Department in common work areas over time as the pandemic unfolded, measuring the effectiveness of interventions meant to discourage such close contact. METHODS: We used a Real-Time Locating System to measure staff groupings in crowded common work areas lasting ten or more minutes. We compared the number of these interactions pre-pandemic with those occurring early and then later in the pandemic, as distancing interventions were suggested and then formalized. Nearly all healthcare workers in the ED were included, and the duration of interactions over time were evaluated as well. RESULTS AND CONCLUSIONS: This study included a total of 12,386 pairs of staff-to-staff encounters over three time periods including just prior to the pandemic, early in the pandemic response, and later in the steady-state pandemic response. Pairs of staff averaged 0.89 high-risk interactions hourly prior to the pandemic, and this continued early in the pandemic with informal recommendations (0.80 high-risk pairs hourly). High-risk staff encounters fell significantly to 0.47 interactions per hour in the steady-state pandemic with formal distancing guidelines in place and decreased patient and staffing volumes. The duration of these encounters remained stable, near 16 min. Close contact between healthcare staff workers did significantly decrease with formal distancing guidelines, though some high-risk interactions remained, warranting additive protective measures such as universal masking.

Development and empirical user-centered evaluation of semantically-based query recommendation for an electronic health record search engine.

OBJECTIVE: The utility of biomedical information retrieval environments can be severely limited when users lack expertise in constructing effective search queries. To address this issue, we developed a computer-based query recommendation algorithm that suggests semantically interchangeable terms based on an initial user-entered query. In this study, we assessed the value of this approach, which has broad applicability in biomedical information retrieval, by demonstrating its application as part of a search engine that facilitates retrieval of information from electronic health records (EHRs). MATERIALS AND METHODS: The query recommendation algorithm utilizes MetaMap to identify medical concepts from search queries and indexed EHR documents. Synonym variants from UMLS are used to expand the concepts along with a synonym set curated from historical EHR search logs. The empirical study involved 33 clinicians and staff who evaluated the system through a set of simulated EHR search tasks. User acceptance was assessed using the widely used technology acceptance model. RESULTS: The search engine's performance was rated consistently higher with the query recommendation feature turned on vs. off. The relevance of computer-recommended search terms was also rated high, and in most cases the participants had not thought of these terms on their own. The questions on perceived usefulness and perceived ease of use received overwhelmingly positive responses. A vast majority of the participants wanted the query recommendation feature to be available to assist in their day-to-day EHR search tasks. DISCUSSION AND CONCLUSION: Challenges persist for users to construct effective search queries when retrieving information from biomedical documents including those from EHRs. This study demonstrates that semantically-based query recommendation is a viable solution to addressing this challenge.

Out of many, one: integrating data in the paediatric cardiovascular environment.

Large volumes of data and multiple computing platforms are now universal components of paediatric cardiovascular medicine, but are in a constant state of evolution. Often, multiple sets of related data reside in disconnected "silos", resulting in clinical, administrative, and research activities that may be duplicative, inefficient, and at times inaccurate. Comprehensive and integrated data solutions are needed to facilitate these activities across congenital heart centres. We describe methodology, key considerations, successful use cases, and lessons learnt in developing an integrated data platform across our congenital heart centre.

Improving the design of patient-generated health data visualizations: design considerations from a Fitbit sleep study.

Interactive data visualization can be a viable way to discover patterns in patient-generated health data and enable health behavior changes. However, very few studies have investigated the design and usability of such data visualization. The present study aimed to (1) explore user experiences with sleep data visualizations in the Fitbit app, and (2) focus on end users' perspectives to identify areas of improvement and potential solutions. The study recruited eighteen pre-medicine college students, who wore Fitbit watches for a two-week sleep data collection period and participated in an exit semi-structured interview to share their experience. A focus group was conducted subsequently to ideate potential solutions. The qualitative analysis identified six pain points (PPs) from the interview data using affinity mapping. Four design solutions were proposed by the focus group to address these PPs and illustrated by a set of mock-ups. The study findings informed four design considerations: (1) usability, (2) transparency and explainability, (3) understandability and actionability, and (4) individualized benchmarking. Further research is needed to examine the design guidelines and best practices of sleep data visualization, to create well-designed visualizations for the general population that enables health behavior changes.

Sleep Patterns of Premedical Undergraduate Students: Pilot Study and Protocol Evaluation.

BACKGROUND: Poor sleep hygiene persists in college students today, despite its heavy implications on adolescent development and academic performance. Although sleep patterns in undergraduates have been broadly investigated, no study has exclusively assessed the sleep patterns of premedical undergraduate students. A gap also exists in the knowledge of how students perceive their sleep patterns compared to their actual sleep patterns. OBJECTIVE: This study aims to address 2 research questions: What are the sleep patterns of premedical undergraduate students? Would the proposed study protocol be feasible to examine the perception of sleep quality and promote sleep behavioral changes in premedical undergraduate students? METHODS: An anonymous survey was conducted with premedical students in the Medical Science Baccalaureate program at an R1: doctoral university in the Midwest United States to investigate their sleep habits and understand their demographics. The survey consisted of both Pittsburg Sleep Quality Index (PSQI) questionnaire items (1-9) and participant demographic questions. To examine the proposed protocol feasibility, we recruited 5 students from the survey pool for addressing the perception of sleep quality and changes. These participants followed a 2-week protocol wearing Fitbit Inspire 2 watches and underwent preassessments, midassessments, and postassessments. Participants completed daily reflections and semistructured interviews along with PSQI questionnaires during assessments. RESULTS: According to 103 survey responses, premedical students slept an average of 7.1 hours per night. Only a quarter (26/103) of the participants experienced good sleep quality (PSQI<5), although there was no significant difference (P=.11) in the proportions of good (PSQI<5) versus poor sleepers (PSQI≥5) across cohorts. When students perceived no problem at all in their sleep quality, 50% (14/28) of them actually had poor sleep quality. Among the larger proportion of students who perceived sleep quality as only a slight problem, 26% (11/43) of them presented poor sleep quality. High stress levels were associated with poor sleep quality. This study reveals Fitbit as a beneficial tool in raising sleep awareness. Participants highlighted Fitbit elements that aid in comprehension such as being able to visualize their sleep stage breakdown and receive an overview of their sleep pattern by simply looking at their Fitbit sleep scores. In terms of protocol evaluation, participants believed that assessments were conducted within the expected duration, and they did not have a strong opinion about the frequency of survey administration. However, Fitbit was found to provide notable variation daily, leading to missing data. Moreover, the Fitbit app's feature description was vague and could lead to confusion. CONCLUSIONS: Poor sleep quality experienced by unaware premedical students points to a need for raising sleep awareness and developing effective interventions. Future work should refine our study protocol based on lessons learned and health behavior theories and use Fitbit as an informatics solution to promote healthy sleep behaviors.

Roles of Health Literacy in Relation to Social Determinants of Health and Recommendations for Informatics-Based Interventions: Systematic Review.

BACKGROUND: Health literacy (HL) is the ability to make informed decisions using health information. As health data and information availability increase due to online clinic notes and patient portals, it is important to understand how HL relates to social determinants of health (SDoH) and the place of informatics in mitigating disparities. OBJECTIVE: This systematic literature review aims to examine the role of HL in interactions with SDoH and to identify feasible HL-based interventions that address low patient understanding of health information to improve clinic note-sharing efficacy. METHODS: The review examined 2 databases, Scopus and PubMed, for English-language articles relating to HL and SDoH. We conducted a quantitative analysis of study characteristics and qualitative synthesis to determine the roles of HL and interventions. RESULTS: The results (n=43) were analyzed quantitatively and qualitatively for study characteristics, the role of HL, and interventions. Most articles (n=23) noted that HL was a result of SDoH, but other articles noted that it could also be a mediator for SdoH (n=6) or a modifiable SdoH (n=14) itself. CONCLUSIONS: The multivariable nature of HL indicates that it could form the basis for many interventions to combat low patient understandability, including 4 interventions using informatics-based solutions. HL is a crucial, multidimensional skill in supporting patient understanding of health materials. Designing interventions aimed at improving HL or addressing poor HL in patients can help increase comprehension of health information, including the information contained in clinic notes shared with patients.

A Neurosurgical Readmissions Reduction Program in an Academic Hospital Leveraging Machine Learning, Workflow Analysis, and Simulation.

BACKGROUND: Predicting 30-day hospital readmissions is crucial for improving patient outcomes, optimizing resource allocation, and achieving financial savings. Existing studies reporting the development of machine learning (ML) models predictive of neurosurgical readmissions do not report factors related to clinical implementation. OBJECTIVES: Train individual predictive models with good performance (area under the receiver operating characteristic curve or AUROC > 0.8), identify potential interventions through semi-structured interviews, and demonstrate estimated clinical and financial impact of these models. METHODS: Electronic health records were utilized with five ML methodologies: gradient boosting, decision tree, random forest, ridge logistic regression, and linear support vector machine. Variables of interest were determined by domain experts and literature. The dataset was split divided 80% for training and validation and 20% for testing randomly. Clinical workflow analysis was conducted using semi-structured interviews to identify possible intervention points. Calibrated agent-based models (ABMs), based on a previous study with interventions, were applied to simulate reductions of the 30-day readmission rate and financial costs. RESULTS: The dataset covered 12,334 neurosurgical intensive care unit (NSICU) admissions (11,029 patients); 1,903 spine surgery admissions (1,641 patients), and 2,208 traumatic brain injury (TBI) admissions (2,185 patients), with readmission rate of 13.13, 13.93, and 23.73%, respectively. The random forest model for NSICU achieved best performance with an AUROC score of 0.89, capturing potential patients effectively. Six interventions were identified through 12 semi-structured interviews targeting preoperative, inpatient stay, discharge phases, and follow-up phases. Calibrated ABMs simulated median readmission reduction rates and resulted in 13.13 to 10.12% (NSICU), 13.90 to 10.98% (spine surgery), and 23.64 to 21.20% (TBI). Approximately $1,300,614.28 in saving resulted from potential interventions. CONCLUSION: This study reports the successful development and simulation of an ML-based approach for predicting and reducing 30-day hospital readmissions in neurosurgery. The intervention shows feasibility in improving patient outcomes and reducing financial losses.

Preoperative Hemodynamics Impact the Benefit of Fenestration on Fontan Postoperative Length of Stay.

BACKGROUND: Utilization of Fontan fenestration varies considerably by center. OBJECTIVES: Using a multicenter Pediatric Heart Network dataset linking surgical and preoperative hemodynamic variables, the authors evaluated factors associated with use of Fontan fenestration and the impact of fenestration on post-Fontan length of stay (LOS). METHODS: Patients 2 to 6 years old at Fontan surgery from 2010 to 2020 with catheterization<1 year prior were included. Factors associated with fenestration were evaluated using multivariable logistic regression adjusting for key covariates. Restrictive cubic spline analysis was used to evaluate potential cut-points for hemodynamic variables associated with longer postoperative LOS stratified by fenestration with multivariable linear regression to evaluate the magnitude of effect. RESULTS: Fenestration was used in 465 of 702 patients (66.2%). Placement of a fenestration was associated with center (range 27%-93% use, P < 0.0001) and Fontan type (OR: 14.1 for lateral tunnel vs extracardiac conduit, P < 0.0001). No hemodynamic variable was independently associated with fenestration. In a multivariable linear model adjusting for center, a center-fenestration interaction, prematurity, preoperative mean pulmonary artery pressure (mPAP), and cardiac index, fenestration was associated with shorter hospital LOS after Fontan (P = 0.0024). The benefit was most pronounced at mPAP ≥13 mm Hg (median LOS: 9 vs 12 days, P = 0.001). CONCLUSIONS: There is wide center variability in use of Fontan fenestration that is not explained by preoperative hemodynamics. Fenestration is independently associated with shorter LOS, and those with mPAP ≥13 mm Hg at pre-Fontan catheterization benefit the most. We propose this threshold as minimal criteria for fenestration.

Adopting a metaverse-based workspace to support research team collaboration: a pilot study from an academic health informatics laboratory.

Objective: This study aimed to understand how a metaverse-based (virtual) workspace can be used to support the communication and collaboration in an academic health informatics lab. Materials and Methods: A survey of lab members (n = 14) was analyzed according to a concurrent triangulation mixed methods design. The qualitative survey data were organized according to the Capability, Opportunity, Motivation, Behavior (COM-B) model and combined to generate personas that represent the overall types of lab members. Additionally, scheduled work hours were analyzed quantitatively to complement the findings of the survey feedback. Results: Four personas, representative of different types of virtual workers, were developed using the survey responses. These personas reflected the wide variety of opinions about virtual work among the participants and helped to categorize the most common feedback. The Work Hours Schedule Sheet analysis showed the low number of possible collaboration opportunities that were utilized compared to the number available. Discussion: We found that informal communication and co-location were not supported by the virtual workplace as we had originally planned. To solve this issue, we offer 3 design recommendations for those looking to implement their own virtual informatics lab. First, labs should establish common goals and norms for virtual workplace interactions. Second, labs should carefully plan the virtual space layout to maximize communication opportunities. Finally, labs should work with their platform of choice to address technical limitations for their lab members to improve user experience. Future work includes a formal, theory-guided experiment with consideration on ethical and behavioral impact.

Developing a Semantically Based Query Recommendation for an Electronic Medical Record Search Engine: Query Log Analysis and Design Implications.

BACKGROUND: An effective and scalable information retrieval (IR) system plays a crucial role in enabling clinicians and researchers to harness the valuable information present in electronic health records. In a previous study, we developed a prototype medical IR system, which incorporated a semantically based query recommendation (SBQR) feature. The system was evaluated empirically and demonstrated high perceived performance by end users. To delve deeper into the factors contributing to this perceived performance, we conducted a follow-up study using query log analysis. OBJECTIVE: One of the primary challenges faced in IR is that users often have limited knowledge regarding their specific information needs. Consequently, an IR system, particularly its user interface, needs to be thoughtfully designed to assist users through the iterative process of refining their queries as they encounter relevant documents during their search. To address these challenges, we incorporated "query recommendation" into our Electronic Medical Record Search Engine (EMERSE), drawing inspiration from the success of similar features in modern IR systems for general purposes. METHODS: The query log data analyzed in this study were collected during our previous experimental study, where we developed EMERSE with the SBQR feature. We implemented a logging mechanism to capture user query behaviors and the output of the IR system (retrieved documents). In this analysis, we compared the initial query entered by users with the query formulated with the assistance of the SBQR. By examining the results of this comparison, we could examine whether the use of SBQR helped in constructing improved queries that differed from the original ones. RESULTS: Our findings revealed that the first query entered without SBQR and the final query with SBQR assistance were highly similar (Jaccard similarity coefficient=0.77). This suggests that the perceived positive performance of the system was primarily attributed to the automatic query expansion facilitated by the SBQR rather than users manually manipulating their queries. In addition, through entropy analysis, we observed that search results converged in scenarios of moderate difficulty, and the degree of convergence correlated strongly with the perceived system performance. CONCLUSIONS: The study demonstrated the potential contribution of the SBQR in shaping participants' positive perceptions of system performance, contingent upon the difficulty of the search scenario. Medical IR systems should therefore consider incorporating an SBQR as a user-controlled option or a semiautomated feature. Future work entails redesigning the experiment in a more controlled manner and conducting multisite studies to demonstrate the effectiveness of EMERSE with SBQR for patient cohort identification. By further exploring and validating these findings, we can enhance the usability and functionality of medical IR systems in real-world settings.

Using Health Forum Data to Assess User Needs for mHealth App Development: A Feasibility Study on Alzheimer's Disease.

Online health forums are used by patients and caregivers as community and information resources, especially for chronic disease management, and could help determine user needs for digital health app design. This study aims to assess the feasibility of using online forum posts on Alzheimer's disease to inform user needs in mobile health application design and whether this process can be automated through text clustering methods. A total of 413 posts were analyzed manually through thematic coding and yielded three themes and nine subthemes for patient and caregiver needs. The external evaluation showed fair to substantial similarity between the automatically and manually derived labels. Four personas were developed to assess the validity of forum-generated needs. These results establish that health forum data can provide sufficient information to understand user needs. However, further refinement of the analysis process and algorithm is necessary to generalize this method to other disease conditions and types of forum data.

User-Centered Evaluation and Design Recommendations for an Internal Medicine Resident Competency Assessment Dashboard.

OBJECTIVES: Clinical Competency Committee (CCC) members employ varied approaches to the review process. This makes the design of a competency assessment dashboard that fits the needs of all members difficult. This work details a user-centered evaluation of a dashboard currently utilized by the Internal Medicine Clinical Competency Committee (IM CCC) at the University of Cincinnati College of Medicine and generated design recommendations. METHODS: Eleven members of the IM CCC participated in semistructured interviews with the research team. These interviews were recorded and transcribed for analysis. The three design research methods used in this study included process mapping (workflow diagrams), affinity diagramming, and a ranking experiment. RESULTS: Through affinity diagramming, the research team identified and organized opportunities for improvement about the current system expressed by study participants. These areas include a time-consuming preprocessing step, lack of integration of data from multiple sources, and different workflows for each step in the review process. Finally, the research team categorized nine dashboard components based on rankings provided by the participants. CONCLUSION: We successfully conducted user-centered evaluation of an IM CCC dashboard and generated four recommendations. Programs should integrate quantitative and qualitative feedback, create multiple views to display these data based on user roles, work with designers to create a usable, interpretable dashboard, and develop a strong informatics pipeline to manage the system. To our knowledge, this type of user-centered evaluation has rarely been attempted in the medical education domain. Therefore, this study provides best practices for other residency programs to evaluate current competency assessment tools and to develop new ones.

Principles for Designing and Developing a Workflow Monitoring Tool to Enable and Enhance Clinical Workflow Automation.

BACKGROUND: Automation of health care workflows has recently become a priority. This can be enabled and enhanced by a workflow monitoring tool (WMOT). OBJECTIVES: We shared our experience in clinical workflow analysis via three cases studies in health care and summarized principles to design and develop such a WMOT. METHODS: The case studies were conducted in different clinical settings with distinct goals. Each study used at least two types of workflow data to create a more comprehensive picture of work processes and identify bottlenecks, as well as quantify them. The case studies were synthesized using a data science process model with focuses on data input, analysis methods, and findings. RESULTS: Three case studies were presented and synthesized to generate a system structure of a WMOT. When developing a WMOT, one needs to consider the following four aspects: (1) goal orientation, (2) comprehensive and resilient data collection, (3) integrated and extensible analysis, and (4) domain experts. DISCUSSION: We encourage researchers to investigate the design and implementation of WMOTs and use the tools to create best practices to enable workflow automation and improve workflow efficiency and care quality.

A READABILITY COMPARISON OF ONLINE SPANISH AND ENGLISH PATIENT EDUCATION MATERIALS ABOUT VISION HEALTH.

PURPOSE: Current United States national guidelines recommend patient education materials (PEMs) be written at a 5th-6th grade level. The objective of this study was to compare the readability of Spanish vision and eye health PEMs to nationally recommended reading levels and to English versions of the same PEMs. METHODS: PEMs were collected from seven online websites of vision-related organizations that provided PEMs with Spanish and English versions. PEMs were downloaded for text to be extracted and analyzed. Readability scoring was performed with Índice Flesch-Szigriszt, Spanish and English Lexile Text Analyzers, and Flesch-Kincaid Grade Level. RESULTS: A total of 484 PEMs with Spanish and English versions were analyzed. Readability for Spanish PEMs was reported at or above the 6th grade level for 57% of articles based on Spanish Lexile scoring and 63% based on Índice Flesch-Szigriszt scoring. Readability for English PEMs was reported at or above the 6th grade level for 66% of articles based on English Lexile scoring and 75% based on Flesch-Kincaid Grade Level scoring. Wilcoxon signed-rank test comparing grade levels translated from Lexile scores for Spanish and English versions of PEMs revealed that Spanish versions of PEMs required higher grade reading levels compared to English versions of PEMs (p < .001). CONCLUSION: Spanish and English PEMs were written above nationally recommended reading levels. Online sources providing multilingual vision and eye health education should consider routinely monitoring PEMs to ensure reading levels meet the literacy needs of their audiences.

User-Centered Evaluation of a Visual Annotation Tool for Rapid Assessment of Pediatric Weight Entry Errors.

Weight entry errors can cause significant patient harm in pediatrics due to pervasive weight-based dosing practices. While computerized algorithms can assist in error detection, they have not achieved high sensitivity and specificity to be further developed as a clinical decision support tool. To train an advanced algorithm, expert-annotated weight errors are essential but difficult to collect. In this study, we developed a visual annotation tool to gather large amounts of expertly annotated pediatric weight charts and conducted a formal user-centered evaluation. Key features of the tool included configurable grid sizes and annotation styles. The user feedback was collected through a structured survey and user clicks on the interface. The results show that the visual annotation tool has high usability (average SUS=86.4). Different combinations of the key features, however, did not significantly improve the annotation efficiency and duration. We have used this tool to collect expert annotations for algorithm development and benchmarking.

A User-Centered Evaluation of a COVID-19 Intelligent Query System (COVID-IQS).

As the fight against COVID-19 continues, it is critical to discover and accumulate knowledge in scientific literature to combat the pandemic. In this work, we shared the experience in developing an intelligent query system on COVID-19 literature. We conducted a user-centered evaluation with 12 researchers in our institution and identified usability issues in four categories: distinct user needs, functionality errors, suboptimal information display, and implementation errors. Furthermore, we shared two lessons for building such a COVID-19 literature search engine. We will deploy the system and continue refining it through multiple phases of evaluation to aid in redesigning the system to accommodate different user roles as well as enhancing repository features to support collaborative information seeking. The successful implementation of the COVID-IQS can support knowledge discovery and hypothesis generation in our institution and can be shared with other institutions to make a broader impact.

Development of a Clinical Decision Support System to Predict Unplanned Cancer Readmissions.

Unplanned 30-day cancer readmissions are an important outcome of cancer hospitalization and can significantly raise mortality rates and costs for both the patient and the hospital. This paper aimed to develop a predictive model using machine learning and electronic health records to predict unplanned 30-day cancer readmissions and further develop it as a clinical decision support system. The three-stage study design followed the 2022 AMIA Artificial Intelligence Evaluation Showcase. In the first stage, the technical performance of the model was determined (81% of AUROC) and contributing factors were identified. In the second stage, the technical feasibility and workflow considerations of using such a predictive model were explored through semi-structured interviews. In the third stage, a decision tree analysis and a cost estimation showed that the model can reduce unplanned readmissions significantly if timely action is taken and that preventing a single readmission may significantly reduce costs.

Development and Evaluation of an Automated Approach to Detect Weight Abnormalities in Pediatric Weight Charts.

Inaccurate body weight measures can cause critical safety events in clinical settings as well as hindering utilization of clinical data for retrospective research. This study focused on developing a machine learning-based automated weight abnormality detector (AWAD) to analyze growth dynamics in pediatric weight charts and detect abnormal weight values. In two reference-standard based evaluation of real-world clinical data, the machine learning models showed good capacity for detecting weight abnormalities and they significantly outperformed the methods proposed in literature (p-value<0.05). A deep learning model with bi-directional long short-term memory networks achieved the best predictive performance, with AUCs ≥0.989 across the two datasets. The positive predictive value and sensitivity achieved by the system suggested more than 98% screening effort reduction potential in weight abnormality detection. Consequently, we hypothesize that the AWAD, when fully deployed, holds great potential to facilitate clinical research and healthcare delivery that rely on accurate and reliable weight measures.

A mobile application to support bedside nurse documentation and care: a time and motion study.

Documentation at the bedside is still often initiated on paper before being entered in electronic charts, even after implementing electronic health records (EHRs). This 2-step process is time-consuming, a potential source of error, and hinders the use of real-time information. We developed the "Bedside mobility" smartphone application to facilitate bedside documentation in the EHR. OBJECTIVE: This study aims to evaluate the impact of our app in 2 wards of a teaching hospital with a pre-post design. MATERIALS AND METHODS: The duration and location of all documentation activities were recorded using a time motion study. RESULTS: Using the app significantly decreased the duration of EHR documentation per hour of observation by 4.10 min (P = 0.003), while the time spent interacting with patient increased by 1.45 min although not significantly. Also, in the intervention period, the average duration of uninterrupted documentation episodes increased by 0.27 min (P = 0.16) and the uninterrupted interaction with patient increased by 8.50 min (P = 0.027). DISCUSSION: By reducing the fragmentation of documentation workflow, decreasing the overall EHR documentation time and allowing nurses to spend more time with their patients, app use led to potential higher quality of care and higher patient satisfaction and may help maintain a smoother workflow. CONCLUSION: Our mobile app has the potential to positively impact bedside nurses' clinical workflow and documentation, as well as patient-provider communication and relationship.