RESUMO
OBJECTIVE: The Emergency Severity Index (ESI) is the most commonly used system in over 70% of all U.S. emergency departments (ED) that uses predicted resource utilization as a means to triage [1], Mistriage, which includes both undertriage and overtriage has been a persistent issue, affecting 32.2% of total ED visits [2]. Our goal is to develop a machine learning framework that predicts patients' resource needs, thereby improving resource allocation during triage. METHODS: This retrospective study analyzed ED visits from the Medical Information Mart for Intensive Care IV, dividing the data into training (80%) and testing (20%) cohorts. We utilized data available during triage, including patient vital signs, age, gender, mode of arrival, medication history, and chief complaint. Azure AutoML was used to create different machine learning models trained to predict the 144 target columns including laboratory panels and imaging modalities as well as medications required during patients' ED visits. The 144 models' performance was evaluated using the area under the receiver operating characteristic curve (AUROC), F1 score, accuracy, precision and recall. RESULTS: A total of 391,472 ED visits were analyzed. 144 Voting ensemble models were created for each target. All frameworks achieved on average an AUC score of 0.82 and accuracy of 0.76. We gathered the feature importance for each target and observed that 'chief complaint', among others, had a high aggregate feature importance across different targets. CONCLUSION: This study shows the high accuracy in predicting resource needs for patients in the ED using a machine learning model. This can greatly improve patient flow and resource allocation in already resource limited emergency departments.
RESUMO
INTRODUCTION: The usage of extracorporeal membrane oxygenation (ECMO) in trauma patients has increased significantly within the past decade. Despite increased research on ECMO application in trauma patients, there remains limited data on factors predicting morbidity and mortality outcome. Therefore, the primary objective of this study is to describe patient characteristics that are independently associated with mortality in ECMO therapy in trauma patients, to further guide future research. METHODS: This retrospective study was conducted using the Trauma Quality Improvement Program database from 2010 to 2019. All adult (age ≥ 16 y) trauma patients that utilized ECMO were included. A Significant differences (P < 0.05) in demographic and clinical characteristics between groups were calculated using an independent t-test for normal distributed continuous values, a Mann-Whitney U test for non-normal distributed values, and a Pearson chi-square test for categorical values. A multivariable regression model was used to identify independent predictors for mortality. A survival flow chart was constructed by using the strongest predictive value for mortality and using the optimal cut-off point calculated by the Youden index. RESULTS: Five hundred forty-two patients were included of whom 205 died. Multivariable analysis demonstrated that the female gender, ECMO within 4 h after presentation, a decreased Glasgow Coma Scale, increased age, units of blood in the first 4 h, and abbreviated injury score for external injuries were independently associated with mortality in ECMO trauma patients. It was found that an external abbreviated injury score of ≥3 had the strongest predictive value for mortality, as patients with this criterion had an overall 29.5% increased risk of death. CONCLUSIONS: There is an ongoing increasing trend in the usage of ECMO in trauma patients. This study has identified multiple factors that are individually associated with mortality. However, more research must be done on the association between mortality and noninjury characteristics like Pao2/Fio2 ratio, acute respiratory distress syndrome classification, etc. that reflect the internal state of the patient.
RESUMO
STUDY OBJECTIVE: Given the popularity of educational blogs and podcasts in medicine, learners and educators need tools to identify trusted and impactful sites. The Social Media Index was a multi-sourced formula to rank the effect of emergency medicine and critical care blogs. In 2022, a key data point for the Social Media Index became unavailable. This bibliometric study aimed to develop a new measure, the Digital Impact Factor, as a replacement. METHODS: The Digital Impact Factor incorporated modern measures of website authority and reach. This formula was applied to a cross-sectional study of active emergency medicine and critical care blogs and podcasts. For each website, we generated a Digital Impact Factor score based on Ahrefs Domain Rating and the follower count of the websites' pages from 8 social media platforms. A series of Spearman correlations provided evidence of association by comparing a rank-ordered list to rank lists derived from the Social Media Index over the last 5 years. The Bland-Altman analysis assessed for agreement. RESULTS: The authors identified 88 relevant websites with a median Ahrefs Domain Rating of 28 (range 0 to 71, maximum 100) and total social media followership count across 8 platforms of 1,828,557. The Domain Rating and individual social media followership scores were normalized based on the highest recorded values to yield the Digital Impact Factor (median 4.57; range 0.02 to 9.50, maximum 10). The correlation between the 2022 Digital Impact Factor and the 2021 Social Media Index was 0.94 (95% confidence interval 0.89 to 0.97; p<.001; n=41 rankings correlated), suggesting that they measure similar constructs. The Bland-Altman plot also demonstrated fair agreement between the 2 scores. CONCLUSION: The Digital Impact Factor is a measure of the relative effect of educational blogs and podcasts within emergency medicine and critical care.
Assuntos
Medicina de Emergência , Mídias Sociais , Humanos , Estudos Transversais , Escolaridade , Blogging , Cuidados CríticosRESUMO
BACKGROUND: To describe the influence of COVID-19 caseload surges and overall capacity in the intensive care unit (ICU) on mortality among US population and census divisions. METHODS: A retrospective analysis of the national COVID ActNow database between January 1, 2021 until March 1, 2022. The main outcome used was COVID-19 weekly mortality rates, which were calculated and incorporated into several generalized estimation of effects models with predictor variables that included ICU bed capacity, as well as ICU capacity used by COVID cases while adjusting for ratios of vaccinations in populations, case density, and percentage of the population over the age of 65. RESULTS: Each 1% increase in general ICU capacity is correlated with approximately 5 more weekly deaths from COVID-19 per 100,000 population and each percentage increase in the number of patients with COVID-19 admitted to the ICU resulted in approximately 10 more COVID-19 deaths per week per 100,000 population. Significant differences in ability to handle caseload surges were observed across US census divisions. CONCLUSIONS: A strong association was observed between COVID-19 ICU surges, overall ICU surge, and increased mortality. Further research is needed to reveal best practices and public health measures to prevent ICU overcrowding amidst future pandemics and disaster responses.
Assuntos
COVID-19 , Humanos , Pandemias , SARS-CoV-2 , Estudos Retrospectivos , Unidades de Terapia IntensivaRESUMO
[This corrects the article DOI: 10.2196/20469.].
RESUMO
With the growing importance of communicating with the public via the web, many industries have used web analytics to provide information that organizations can use to better achieve their goals. Although the importance of health care websites has also grown, the health care industry has been slower to adopt the use of web analytics. Web analytics are the measurement, collection, analysis, and reporting of internet data used to measure direct user interaction. Our objective is to provide generalized methods for using web analytics as key performance metrics to evaluate websites and outline actionable recommendations for improvement. By deconstructing web analytic categories such as engagement, users, acquisition, content, and platform, we describe how web analytics are used to evaluate websites and how improvements can be made using this information. Engagement is how a user interacts with a website. It can be evaluated using the daily active users to monthly active users (DAU/MAU) ratio, bounce rate, pages viewed, and time on site. Poor engagement indicates potential problems with website usability. Users pertains to demographic information regarding the users interacting with a website. This data can help administrators understand who is engaging with their website. Acquisition refers to the overall website traffic and the method of traffic, which allows administrators to see how people are accessing their website. This information helps websites expand their methods of attracting users. Content refers to the overall relevancy, accuracy, and trustworthiness of a website's content. If a website has poor content, it will likely experience difficulty with user engagement. Finally, platform refers to the technical aspects of how people access a website. It includes both the internet browsers and devices used. By providing detailed descriptions of these categories, we have identified how web administrators can use web analytics to systematically assess their websites. We have also provided generalized recommendations for actionable improvements. By introducing the potential of web analytics to augment usability and the conversion rate, we hope to assist health care organizations in better communicating with the public and therefore accomplishing the goals of their websites.
Assuntos
Internet , Software , Atenção à Saúde , HumanosRESUMO
OBJECTIVES: Hysteroscopic adhesiolysis (HA) remains the mainstay on treatment for intrauterine adhesions (IUA). The fertility outcome of patients with moderate and severe intrauterine adhesions after HA is still far from satisfactory. Estrogen combined with progesterone is the most common treatment; however, they do not help in improving the fertility rate to the maximum because of the limitations. This retrospective, non-randomized controlled study will assess the effects of traditional Chinese medicine Yangmo decoction after HA in restoration of the endometrium and improvement of the fertility rate. METHODS: A total of 427 patients, who met the inclusion criteria, aged between 20 and 45 years and diagnosed with moderate or severe IUA underwent HA at the Third Xiangya Hospital from January to August 2021, were enrolled for this study. Participants were assigned into 2 groups: A Yangmo decoction group (n=213, patients were given Yangmo decoction consisting of Ginseng flower, Sanchi flower, Daidai flower, Snow lotus, Licorice and so on after HA), and an estrogen and progesterone group (n=214, patients were given estrogen and progesterone after HA). The following basic information was collected retrospectively for both groups, including age, parity, history of abortion, menstrual status, and times of hysteroscopic interventions. American Fertility Society (AFS) score was used by a senior surgeon and the density of opening of endometrial glands was evaluated during HA. The parameters were obtained from three-dimensional transvaginal ultrasound (3D-TVUS) preoperatively and postoperatively, to evaluate the efficacy of Yangmo decoction, estrogen, and progesterone. All patients were followed up on telephone to determine the fertility rate until 6 months from the last HA. RESULTS: Based on the basic information collected preoperatively, there were no significant differences between the groups (all P>0.05). Postoperatively, patients in the Yangmo decoction group had a better surgical success rate with a more significant AFS reduction (P<0.001), better density of opening of endometrial glands in the uterine cavity (P<0.000 1) after HA, and a better fertility rate (40.4%) in the time of 6 months after the last HA than those of the estrogen and progesterone group. CONCLUSIONS: Yangmo decoction has better therapeutic efficacy in the treatment of intrauterine adhesion after HA than the combined effect of estrogen and progesterone. Yangmo decoction helps restore the endometrium and improve the fertility rate, therefore, it can be adopted as a routine practice for IUA patients who have fertility requirements.
Assuntos
Progesterona , Adulto , Humanos , Pessoa de Meia-Idade , Adulto Jovem , Estrogênios/uso terapêutico , Medicina Tradicional Chinesa , Progesterona/uso terapêutico , Estudos RetrospectivosRESUMO
BACKGROUND: Health care organizations are tasked with providing web-based health resources and information. Usability refers to the ease of user experience on a website. In this study, we conducted a usability analysis of academic medical centers in the United States, which, to the best of our knowledge, has not been previously carried out. OBJECTIVE: The primary aims of the study were to the following: (1) adapt a preexisting usability scoring methodology to academic medical centers; (2) apply and test this methodology on a sample set of academic medical center websites; and (3) make recommendations from these results on potential areas of improvements for our sample of academic medical center websites. METHODS: All website usability testing took place from June 1, 2020, to December 15, 2020. We replicated a methodology developed in previous literature and applied it to academic medical centers. Our sample included 73 US academic medical centers. Usability was split into four broad categories: accessibility (the ability of those with low levels of computer literacy to access and navigate the hospital's website); marketing (the ability of websites to be found through search engines and the relevance of descriptions to the links provided); content quality (grammar, frequency of information updates, material relevancy, and readability); and technology (download speed, quality of the programming code, and website infrastructure). Using these tools, we scored each website in each category. The composite of key factors in each category contributed to an overall "general usability" score for each website. An overall score was then calculated by applying a weighted percentage across all factors and was used for the final "overall usability" ranking. RESULTS: The category with the highest average score was technology, with a 0.82 (SD 0.068, SE 0.008). The lowest-performing category was content quality, with an average of 0.22 (SD 0.069, SE 0.008). As these numbers reflect weighted percentages as an integer, the higher the score, the greater the overall usability in that category. CONCLUSIONS: Our data suggest that technology, on average, was the highest-scored variable among academic medical center websites. Because website functionality is essential to a user's experience, it is justified that academic medical centers invest in optimal website performance. The overall lowest-scored variable was content quality. A potential reason for this may be that academic medical center websites are usually larger in size, making it difficult to monitor the increased quantity of content. An easy way to improve this variable is to conduct more frequent website audits to assess readability, grammar, and relevance. Marketing is another area in which these organizations have potential for improvement. Our recommendation is that organizations utilize search engine optimization techniques to improve their online visibility and discoverability.
Assuntos
Compreensão , Ferramenta de Busca , Centros Médicos Acadêmicos , Humanos , Internet , Estados UnidosRESUMO
Despite advances in digital technology that have resulted in more people accessing information via mobile devices, little is known about reading comprehension on mobile phones. This research investigated the impact of reading format by comparing sensitivity to misinformation presented either in printed texts or in digital format on mobile phones to readers of English versus Chinese. Participants read pairs of short newspaper-style articles containing a critical piece of information that was either retracted or not retracted, and were later assessed on their memory for critical and general details, as well as inferential judgements related to the retracted information. The average results replicated previous evidence that repeating the original misinformation at the time of retraction enhanced memory updating. However, reading on a mobile phone reduced the likelihood that readers noticed the retraction and updated their memory with alternative information in both language groups and reduced the extent to which inferences were modified by the alternative information in readers of Chinese but not English. Chinese readers showed significantly better general memory, but were more affected by the continued influence of the misinformation. These differences between Chinese and English-speaking participants may reflect cultural influences on the tendency to apply a dialectical rather than an analytic reasoning strategy and incorporate contradictory information into the memory representation of a discourse or event.
Assuntos
Comunicação , Leitura , Compreensão , Humanos , Julgamento , MemóriaRESUMO
Physicians, nurses, and other health care providers initiated the #GetMePPE movement on Twitter to spread awareness of the shortage of personal protective equipment (PPE) during the coronavirus disease (COVID-19) pandemic. Dwindling supplies, such as face masks, gowns and goggles, and inadequate production to meet increasing demand have placed health care workers and patients at risk. The momentum of the #GetMePPE Twitter hashtag resulted in the creation of a petition to urge public officials to address the PPE shortage through increased funding and production. Simultaneously, the GetUsPPE.org website was launched through the collaboration of physicians and software engineers to develop a digital platform for the donation, request, and distribution of multi-modal sources of PPE. GetUsPPE.org and #GetMePPE were merged in an attempt to combine public engagement and advocacy on social media with the coordination of PPE donation and distribution. Within 10 days, over 1800 hospitals and PPE suppliers were registered in a database that enabled the rapid coordination and distribution of scarce and in-demand materials. One month after its launch, the organization had distributed hundreds of thousands of PPE items and had built a database of over 6000 PPE requesters. The call for action on social media and the rapid development of this digital tool created a productive channel for the public to contribute to the health care response to COVID-19 in meaningful ways. #GetMePPE and GetUsPPE.org were able to mobilize individuals and organizations outside of the health care system to address the unmet needs of the medical community. The success of GetUsPPE.org demonstrates the potential of digital tools as a platform for larger health care institutions to rapidly address urgent issues in health care. In this paper, we outline this process and discuss key factors determining success.