Search

Purpose: To assess the accuracy and precision of prosthetically driven implant placement achieved through static computer-aided implant surgery by analyzing the linear and angular deviations of implants. Materials and Methods: A total of 53 implants were included in the study. The implants were positioned using either tooth-supported templates or tooth-and-tissue-supported templates with fixation pins. Two distinct guided surgery approaches were used: pilot drill guided and fully guided. 3D data from the implant planning phase was superimposed with the 3D data from the final implant positions using the "Treatment Evaluation" tool within coDiagnostiX implant planning software (Straumann). This enabled the automatic calculation of deviations in implant placement accuracy. Results: The average angular deviation observed was 3.90 degrees. For linear deviations, the mean 3D deviation was 1.04 mm at the most coronal point of the implants and 1.56 mm at the implant apex. Conclusions: This research demonstrates the feasibility of a digital workflow for guided implant surgery, offering a promising treatment option. Nonetheless, it is important to note that deviations do occur, particularly in the apical region of the implant. Care should be taken, particularly in cases of limited bone availability. [ABSTRACT FROM AUTHOR]

The article shares views on opportunities and challenges posed by big data (BD), mobile health and artificial intelligence to dentistry and craniofacial research. Topics discussed include concerns about privacy, security and data sharing in relation to the use of BD analysis, the Dental, Oral, Medical Epidemiological (DOME) electronic records-based BD study, and the role of combining electronic health record with mobile health tools in improving data sets and in advancing BD research.

In recent years, the role of Artificial Intelligence (AI) in medical imaging has become increasingly prominent, with the majority of AI applications approved by the FDA being in imaging and radiology in 2023. The surge in AI model development to tackle clinical challenges underscores the necessity for preparing high-quality medical imaging data. Proper data preparation is crucial as it fosters the creation of standardized and reproducible AI models while minimizing biases. Data curation transforms raw data into a valuable, organized, and dependable resource and is a fundamental process to the success of machine learning and analytical projects. Considering the plethora of available tools for data curation in different stages, it is crucial to stay informed about the most relevant tools within specific research areas. In the current work, we propose a descriptive outline for different steps of data curation while we furnish compilations of tools collected from a survey applied among members of the Society of Imaging Informatics (SIIM) for each of these stages. This collection has the potential to enhance the decision-making process for researchers as they select the most appropriate tool for their specific tasks.

ObjectiveAlthough supervised machine learning is popular for information extraction from clinical notes, creating large annotated datasets requires extensive domain expertise and is time-consuming. Meanwhile, large language models (LLMs) have demonstrated promising transfer learning capability. In this study, we explored whether recent LLMs could reduce the need for large-scale data annotations.Materials and methodsWe curated a dataset of 769 breast cancer pathology reports, manually labeled with 12 categories, to compare zero-shot classification capability of the following LLMs: GPT-4, GPT-3.5, Starling, and ClinicalCamel, with task-specific supervised classification performance of 3 models: random forests, long short-term memory networks with attention (LSTM-Att), and the UCSF-BERT model.ResultsAcross all 12 tasks, the GPT-4 model performed either significantly better than or as well as the best supervised model, LSTM-Att (average macro F1-score of 0.86 vs 0.75), with advantage on tasks with high label imbalance. Other LLMs demonstrated poor performance. Frequent GPT-4 error categories included incorrect inferences from multiple samples and from history, and complex task design, and several LSTM-Att errors were related to poor generalization to the test set.DiscussionOn tasks where large annotated datasets cannot be easily collected, LLMs can reduce the burden of data labeling. However, if the use of LLMs is prohibitive, the use of simpler models with large annotated datasets can provide comparable results.ConclusionsGPT-4 demonstrated the potential to speed up the execution of clinical NLP studies by reducing the need for large annotated datasets. This may increase the utilization of NLP-based variables and outcomes in clinical studies.

The International Classification of Diseases, 11th Revision (ICD-11) has significantly improved the ability to navigate coding challenges beyond prior iterations of the ICD. Commonly encountered sources of complexity in clinical documentation include coding of uncertain and "ruled out" diagnoses. Assessing official international guidelines and rules, this paper documents extensive variation across countries in existing practices for coding and reporting unconfirmed and "ruled out" clinical concepts in ICD-10 (and modifications thereof). The design of ICD-11 is intended to mitigate these coding challenges by introducing postcoordination, expanding the range of codable clinical concepts, and offering clearer guidance in the ICD-11 Reference Guide. ICD-11 offers substantial progress towards more precise capture of uncertain and "ruled out" diagnoses, including international consensus on coding rules for these historically challenging clinical concepts. However, we identify the need for further clarification of the concepts of "provisional diagnosis" and "differential diagnosis."

Digital heritage portal interfaces are generally similar to digital library and search engine interfaces in displaying search results as a list of brief metadata records. The knowledge organization and search result display of these systems are item-centric, with little support for identifying relationships between items. This paper proposes a knowledge graph system and visualization interface as a promising solution for digital heritage systems to support users in browsing related items, understanding the relationships between items, and synthesizing a narrative on an issue. The paper discusses design issues for the knowledge graph, graph database, and graph visualization, and offers recommendations based on the authors' experience in developing three knowledge graph systems for archive and digital humanities resources: the Zubir Said personal archive collection at the Nanyang Academy of Fine Arts, Singapore; Singapore Pioneers social network; and Polyglot Medicine knowledge graph of Asian traditional and herbal medicine. Lessons learned from a small user study are incorporated in the discussion. [ABSTRACT FROM AUTHOR]

This column is intended to address the kinds of knotty problems and dilemmas with which many scholars grapple in studying health professions education. In this article, the authors address the challenges in proofreading a manuscript. Emerging researchers might think that someone in the production team will catch any errors. This may not always be the case. We emphasize the importance of guiding mentees to take the process of preparing a manuscript for submission seriously.

Kidney failure is particularly common in the United States, where it affects over 700,000 individuals. It is typically treated through repeated sessions of hemodialysis to filter and clean the blood. Hemodialysis requires vascular access, in about 70% of cases through an arteriovenous fistula (AVF) surgically created by connecting an artery and vein. AVF take 6 weeks or more to mature. Mature fistulae often require intervention, most often percutaneous transluminal angioplasty (PTA), also known as fistulaplasty, to maintain the patency of the fistula. PTA is also the first-line intervention to restore blood flow and prolong the use of an AVF, and many patients undergo the procedure multiple times. Although PTA is important for AVF maturation and maintenance, research into predictive models of AVF function following PTA has been limited. Therefore, in this paper we hypothesize that based on patient-specific information collected during PTA, a predictive model can be created to help improve treatment planning. We test a set of rich, multimodal data from 28 patients that includes medical history, AVF blood flow, and interventional angiographic imaging (specifically excluding any post-PTA measurements) and build deep hybrid neural networks. A hybrid model combining a 3D convolutional neural network with a multi-layer perceptron to classify AVF was established. We found using this model that we were able to identify the association between different factors and evaluate whether the PTA procedure can maintain primary patency for more than 3 months. The testing accuracy achieved was 0.75 with a weighted F1-score of 0.75, and AUROC of 0.75. These results indicate that evaluating multimodal clinical data using artificial neural networks can predict the outcome of PTA. These initial findings suggest that the hybrid model combining clinical data, imaging and hemodynamic analysis can be useful to treatment planning for hemodialysis. Further study based on a large cohort is needed to refine the accuracy and model efficiency.

The Journal of Management Information Systems (JMIS) is celebrating its fifth decade of publication and is committed to publishing research papers that make significant contributions to the field of information systems. The journal's editors have an inclusive understanding of the field and aim to reflect and shape its growth and evolution. Over the years, JMIS has published papers on various topics, including the economics of IS, strategic deployment of IT, design research, neuroscience in IS research, behavioral cybersecurity, health informatics, and AI-human collaboration. The journal also recognizes its responsibility to support the well-being of society and explores the societal impacts of IT-driven change. The current issue features papers on topics such as the use of body-worn cameras in policing, technological innovation, crowdfunding, chatbots, sentiment analysis, cloud storage and security breaches, cybersecurity risk management, software architecture, and turnover of IT professionals. [Extracted from the article]

ObjectiveBlockchain has emerged as a potential data-sharing structure in healthcare because of its decentralization, immutability, and traceability. However, its use in the biomedical domain is yet to be investigated comprehensively, especially from the aspects of implementation and evaluation, by existing blockchain literature reviews. To address this, our review assesses blockchain applications implemented in practice and evaluated with quantitative metrics.Materials and methodsThis systematic review adapts the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework to review biomedical blockchain papers published by August 2023 from 3 databases. Blockchain application, implementation, and evaluation metrics were collected and summarized.ResultsFollowing screening, 11 articles were included in this review. Articles spanned a range of biomedical applications including COVID-19 medical data sharing, decentralized internet of things (IoT) data storage, clinical trial management, biomedical certificate storage, electronic health record (EHR) data sharing, and distributed predictive model generation. Only one article demonstrated blockchain deployment at a medical facility.DiscussionEthereum was the most common blockchain platform. All but one implementation was developed with private network permissions. Also, 8 articles contained storage speed metrics and 6 contained query speed metrics. However, inconsistencies in presented metrics and the small number of articles included limit technological comparisons with each other.ConclusionWhile blockchain demonstrates feasibility for adoption in healthcare, it is not as popular as currently existing technologies for biomedical data management. Addressing implementation and evaluation factors will better showcase blockchain's practical benefits, enabling blockchain to have a significant impact on the health sector.

OBJECTIVES: This study sought to capture current digital health company experiences integrating with electronic health records (EHRs), given new federally regulated standards-based application programming interface (API) policies. MATERIALS AND METHODS: We developed and fielded a survey among companies that develop solutions enabling human interaction with an EHR API. The survey was developed by the University of California San Francisco in collaboration with the Office of the National Coordinator for Health Information Technology, the California Health Care Foundation, and ScaleHealth. The instrument contained questions pertaining to experiences with API integrations, barriers faced during API integrations, and API-relevant policy efforts. RESULTS: About 73% of companies reported current or previous use of a standards-based EHR API in production. About 57% of respondents indicated using both standards-based and proprietary APIs to integrate with an EHR, and 24% worked about equally with both APIs. Most companies reported use of the Fast Healthcare Interoperability Resources standard. Companies reported that standards-based APIs required on average less burden than proprietary APIs to establish and maintain. However, companies face barriers to adopting standards-based APIs, including high fees, lack of realistic clinical testing data, and lack of data elements of interest or value. DISCUSSION: The industry is moving toward the use of standardized APIs to streamline data exchange, with a majority of digital health companies using standards-based APIs to integrate with EHRs. However, barriers persist. CONCLUSION: A large portion of digital health companies use standards-based APIs to interoperate with EHRs. Continuing to improve the resources for digital health companies to find, test, connect, and use these APIs without special effort will be crucial to ensure future technology robustness and durability.

Background: Asynchronous telepsychiatry (ATP) consultations are a novel form of psychiatric consultation. Studies comparing patient and provider satisfaction for ATP with that for synchronous telepsychiatry (STP) do not exist. Methods: This mixed-methods study is a secondary analysis of patients' and primary care providers' (PCPs) satisfaction from a randomized clinical trial of ATP compared with STP. Patients and their PCPs completed satisfaction surveys, and provided unstructured feedback about their experiences with either ATP or STP. Differences in patient satisfaction were assessed using mixed-effects logistic regression models, and the qualitative data were analyzed using thematic analysis with an inductive coding framework. Results: Patient satisfaction overall was high with 84% and 97% of respondents at 6 months reported being somewhat or completely satisfied with ATP and STP, respectively. Patients in the STP group were more likely to report being completely satisfied, to recommend the program to a friend, and to report being comfortable with their care compared with ATP (all p < 0.05). However, there was no difference between the patients in ATP and STP in perceived change in clinical outcomes (p = 0.51). The PCP quantitative data were small, and thus only summarized descriptively. Conclusions: Patients expressed their overall satisfaction with both STP and ATP. Patients in ATP reported more concerns about the process, likely because feedback after ATP was slower than that after STP consultations. PCPs had no apparent preference for STP or ATP, and reported implementing the psychiatrists' recommendations for both groups when such recommendations were made, which supports our previous findings. Trial Registration: ClinicalTrials.gov NCT02084979; https://clinicaltrials.gov/ct2/show/NCT02084979.

Objectives: The objectives of this retrospective study were to analyze telehealth utilization for two specialty care practices: oral medicine (OM) and oral and maxillofacial surgery (OMFS) during the first 2 years of the pandemic, its impact as a new treatment modality and on participating providers, as well as identify the type of patient visit that most readily adopted telehealth. Methods: Retrospective study of patients who sought specialty services, OM and OMFS, at an outpatient clinic in a university health system setting between March 1, 2019, and February 28, 2022. Source data were obtained from Epic, an electronic medical record application. Data were graphed using Tableau and Microsoft Excel software. Statistical analysis was performed utilizing chi-squared test and analysis of variance (ANOVA). Results: OMFS utilized telehealth 12% of the time, and OM 8% of the time. The majority (87%) of telehealth visits were for return patients (RPs). Compared with the first year of the pandemic, there was a decrease in the number of telehealth visits in the second year (p = 0.0001). As of August 2022, new patient (NP) telehealth encounters have largely returned to prepandemic levels (0-1.5%), whereas RP telehealth visits remained at an average level of 11.4% (9.4-12.4%). Surveyed providers consider telehealth as an effective complement to in-person care and will continue its use (4.2/5 Likert scale). Conclusions: Telehealth has become a viable pathway of care for OM and OMFS who previously did not utilize the remote platform to deliver healthcare. As a new treatment modality, telehealth is perceived as impactful in increasing access to specialty care by participating providers. NP visits are now almost completely in person, but telehealth continues for RPs. Ongoing demand for telehealth highlights urgency to develop appropriate standards and effective remote diagnostic/monitoring tools to maximize telehealth's capability to leverage finite health care resources and increase access to specialty care.

BackgroundNearly three in four U.S. medical students graduate with debt in six-figure dollar amounts which impairs students emotionally and academically and impacts their career choices and lives long after graduation. Schools have yet to develop systems-level solutions to address the impact of debt on students' well-being. The objectives of this study were to identify students at highest risk for debt-related stress, define the impact on medical students' well-being, and to identify opportunities for intervention.MethodsThis was a mixed methods, cross-sectional study that used quantitative survey analysis and human-centered design (HCD). We performed a secondary analysis on a national multi-institutional survey on medical student wellbeing, including univariate and multivariate logistic regression, a comparison of logistic regression models with interaction terms, and analysis of free text responses. We also conducted semi-structured interviews with a sample of medical student respondents and non-student stakeholders to develop insights and design opportunities.ResultsIndependent risk factors for high debt-related stress included pre-clinical year (OR 1.75), underrepresented minority (OR 1.40), debt $20-100 K (OR 4.85), debt >$100K (OR 13.22), private school (OR 1.45), West Coast region (OR 1.57), and consideration of a leave of absence for wellbeing (OR 1.48). Mental health resource utilization (p = 0.968) and counselors (p = 0.640) were not protective factors against debt-related stress. HCD analysis produced 6 key insights providing additional context to the quantitative findings, and associated opportunities for intervention.ConclusionsWe used an innovative combination of quantitative survey analysis and in-depth HCD exploration to develop a multi-dimensional understanding of debt-related stress among medical students. This approach allowed us to identify significant risk factors impacting medical students experiencing debt-related stress, while providing context through stakeholder voices to identify opportunities for system-level solutions.

BackgroundVirtual activities, hybrid work and virtual mentoring have become part of the ongoing milieu of academic medicine. As the shift to remote mentoring continues to evolve, it is now possible to adapt, refine, and improve tools to support thriving mentoring relationships that take place virtually. This study explores strategies for virtual mentoring as a cornerstone for effective training programs among senior mentors participating in an ongoing mentoring program.MethodsWe conducted a qualitative study among prior and current participants of an ongoing "Mentoring the Mentors" program about key strategies for optimizing virtual mentoring. Data were coded and analyzed following a thematic analysis approach.ResultsRespondents were mostly female (62%), white (58%), and associate (39%) or full professors (32%). We found that, with the expansion of hybrid and fully remote work, there are now fewer opportunities for informal but important chance meetings between mentors and mentees; however, virtual mentoring provides opportunities to compensate for reduced interactivity normally experienced in the workplace. The heightened need to plan and be more deliberate in the virtual sphere was woven throughout narratives and was the foundation of most recommendations. Specifically, a central obstacle for respondents was that spontaneous conversations were harder to initiate because virtual conversations are expected to have set agendas.ConclusionsDeveloping new ways to maintain meaningful interpersonal relationships in a virtual training environment, including opportunities for serendipitous and informal engagement, is critical to the success of virtual mentoring programs.

BackgroundSmartphone apps may provide an opportunity to deliver mental health resources and interventions in a scalable and cost-effective manner. However, young people from marginalized and underserved groups face numerous and unique challenges to accessing, engaging with, and benefiting from these apps.ObjectiveThis study aims to better understand the acceptability (ie, perceived usefulness and satisfaction with an app) and feasibility (ie, the extent to which an app was successfully used) of mental health apps for underserved young people. A secondary aim was to establish whether adaptations can be made to increase the accessibility and inclusivity of apps for these groups.MethodsWe conducted 2 sequential studies, consisting of a systematic literature review of mental health apps for underserved populations followed by a qualitative study with underserved young male participants (n=20; age: mean 19). Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, an electronic search of 5 databases was conducted in 2021. The search yielded 18,687 results, of which 14 articles met the eligibility criteria.ResultsThe included studies comprised a range of groups, including those affected by homelessness, having physical health conditions, living in low- and middle-income countries, and those with sexual and gender minority identities. Establishing and maintaining user engagement was a pervasive challenge across mental health apps and populations, and dropout was a reported problem among nearly all the included studies. Positive subjective reports of usability, satisfaction, and acceptability were insufficient to determine users' objective engagement.ConclusionsDespite the significant amount of funding directed to the development of mental health apps, juxtaposed with only limited empirical evidence to support their effectiveness, few apps have been deliberately developed or adapted to meet the heterogeneous needs of marginalized and underserved young people. Before mental health apps are scaled up, a greater understanding is needed of the types of services that more at-risk young people and those in limited-resource settings prefer (eg, standard vs digital) followed by more rigorous and consistent demonstrations of acceptability, effectiveness, and cost-effectiveness. Adopting an iterative participatory approach by involving young people in the development and evaluation process is an essential step in enhancing the adoption of any intervention, including apps, in "real-world" settings and will support future implementation and sustainability efforts to ensure that marginalized and underserved groups are reached.Trial registrationPROSPERO CRD42021254241; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=254241.

BackgroundIn 2011, the American Board of Medical Specialties established clinical informatics (CI) as a subspecialty in medicine, jointly administered by the American Board of Pathology and the American Board of Preventive Medicine. Subsequently, many institutions created CI fellowship training programs to meet the growing need for informaticists. Although many programs share similar features, there is considerable variation in program funding and administrative structures.ObjectivesThe aim of our study was to characterize CI fellowship program features, including governance structures, funding sources, and expenses.MethodsWe created a cross-sectional online REDCap survey with 44 items requesting information on program administration, fellows, administrative support, funding sources, and expenses. We surveyed program directors of programs accredited by the Accreditation Council for Graduate Medical Education between 2014 and 2021.ResultsWe invited 54 program directors, of which 41 (76%) completed the survey. The average administrative support received was $27,732/year. Most programs (85.4%) were accredited to have two or more fellows per year. Programs were administratively housed under six departments: Internal Medicine (17; 41.5%), Pediatrics (7; 17.1%), Pathology (6; 14.6%), Family Medicine (6; 14.6%), Emergency Medicine (4; 9.8%), and Anesthesiology (1; 2.4%). Funding sources for CI fellowship program directors included: hospital or health systems (28.3%), clinical departments (28.3%), graduate medical education office (13.2%), biomedical informatics department (9.4%), hospital information technology (9.4%), research and grants (7.5%), and other sources (3.8%) that included philanthropy and external entities.ConclusionCI fellowships have been established in leading academic and community health care systems across the country. Due to their unique training requirements, these programs require significant resources for education, administration, and recruitment. There continues to be considerable heterogeneity in funding models between programs. Our survey findings reinforce the need for reformed federal funding models for informatics practice and training.

There is increasing interest in understanding potential bias in medical education. We used natural language processing (NLP) to evaluate potential bias in clinical clerkship evaluations. Data from medical evaluations and administrative databases for medical students enrolled in third-year clinical clerkship rotations across two academic years. We collected demographic information of students and faculty evaluators to determine gender/racial concordance (i.e., whether the student and faculty identified with the same demographic). We used a multinomial log-linear model for final clerkship grades, using predictors such as numerical evaluation scores, gender/racial concordance, and sentiment scores of narrative evaluations using the SentimentIntensityAnalyzer tool in Python. 2037 evaluations from 198 students were analyzed. Statistical significance was defined as P

Introduction Disease and non-battle injuries (DNBIs) cause substantial losses among military personnel. NATO has monitored DNBIs among its personnel since 1996 using multiple versions of a tool now called EpiNATO-2, but the surveillance system has never been systematically evaluated. Following a request from NATO to the CDC, the objective of this study was to assess surveillance system attributes of EpiNATO-2 using CDC's updated guidelines for evaluating public health surveillance systems. Materials and Methods Between June and October 2022, a literature review and key informant interviews were conducted to assess the following attributes: usefulness, simplicity, flexibility, data quality, acceptability, sensitivity, positive predictive value, representativeness, timeliness, stability, informatics system quality, informatics service quality, and informatics interoperability. Key informant interviews were conducted in Kosovo, Germany, and remotely with EpiNATO-2 users spanning three levels: clinical and data entry personnel (tactical level); regional medical and public health officers (operational level); and senior commanders and other governmental entities (strategic level). Results Fourteen EpiNATO-2 users participated in interviews, representing 3 of the 5 major NATO missions, 3 partner entities, and 7 nationalities. All users (100%) reported that the system did not meet their needs, with most users noting the following challenges: lack of clearly defined system objectives; poor data quality due to ambiguous case definitions and frequently unsubmitted reports (37% missing during January to June 2022); long delay between the occurrence of health events and the availability of corresponding data (≥2 weeks); and an antiquated and inflexible data management system. Overall, performance was deemed unsatisfactory on 11 of the 13 attributes. Conclusions This multinational sample of EpiNATO-2 users at all military levels reported that the system is currently not useful with respect to its stated objectives. Opportunities exist to improve the performance and usefulness of EpiNATO-2: improve case definitions, modernize data infrastructure, and regularly evaluate the surveillance system. [ABSTRACT FROM AUTHOR]

Introduction: We developed a mobile phone logbook application called LogMyScan. The study objectives were to evaluate a number of domains as per the technology acceptance model. Methods: A prospective pilot cohort study was conducted using a version of LogMyScan and reported according to Statement on Reporting of Evaluation studies in Health Informatics. Prospective participants were directed to a website which provided information and links. Participants were recruited via email distribution lists and social media. A task list was provided, which included entering simulated scan data and navigating the application, prior to completing a questionnaire. Questions were aligned to technology acceptance model domains, and Cronbach's alpha was calculated to assess reliability. Results: There were 49 participants and 7 were unable to complete the image upload and editing step. Levels of agreement for usability, educational and governance/security aspects were generally good. The desirability of existing and proposed features was high for images and video clip handling, feedback and reflection and less for motivational notifications and benchmarking. Comments identified some limitations and issues on the Android platform. Cronbach's alpha demonstrated good to excellent reliability: 0.87 (95% confidence interval, 0.79–0.91) for usability, educational and governance/security and 0.86 (95% confidence interval, 0.78–0.91) for desirability of existing and proposed features. Conclusion: There was generally high perceived ease of use, usefulness, attitude towards use and behavioural intention to use LogMyScan. Further research is needed to evaluate LogMyScan for future iterations, allowing recruitment of a larger number of participants and evaluating user expectations prior to using, and at timed intervals after using. [ABSTRACT FROM AUTHOR]

Objectives Clinical Data Warehouses (CDW) are the designated infrastructures to enable access and analysis of large quantities of electronic health record data. Building and managing such systems implies extensive "data work" and coordination between multiple stakeholders. Our study focuses on the challenges these stakeholders face when designing, operating, and ensuring the durability of CDWs for research. Materials and Methods We conducted semistructured interviews with 21 professionals working with CDWs from France and Belgium. All interviews were recorded, transcribed verbatim, and coded inductively. Results Prompted by the AI boom, healthcare institutions launched initiatives to repurpose data they were generating for care without a clear vision of how to generate value. Difficulties in operating CDWs arose quickly, strengthened by the multiplicity and diversity of stakeholders involved and grand discourses on the possibilities of CDWs, disjointed from their actual capabilities. Without proper management of the information flows, stakeholders struggled to build a shared vision. This was evident in our interviewees' contrasting appreciations of what mattered most to ensure data quality. Participants explained they struggled to manage knowledge inside and across institutions, generating knowledge loss, repeated mistakes, and impeding progress locally and nationally. Discussion and conclusion Management issues strongly affect the deployment and operation of CDWs. This may stem from a simplistic linear vision of how this type of infrastructure operates. CDWs remain promising for research, and their design, implementation, and operation require careful management if they are to be successful. Building on innovation management, complex systems, and organizational learning knowledge will help. [ABSTRACT FROM AUTHOR]

Background There are significant disparities in access and utilization of patient portals by age, language, race, and ethnicity. Materials and Methods We developed ambulatory and inpatient portal activation equity dashboards to understand disparities in initial portal activation, identify targets for improvement, and enable monitoring of interventions over time. We selected key metrics focused on episodes of care and filters to enable high-level overviews and granular data selection to meet the needs of health system leaders and individual clinical units. Results In addition to highlighting disparities by age, preferred language, race and ethnicity, and insurance payor, the dashboards enabled development and monitoring of interventions to improve portal activation and equity. Discussion and Conclusions Data visualization tools that provide easily accessible, timely, and customizable data can enable a variety of stakeholders to understand and address healthcare disparities, such as patient portal activation. Further institutional efforts are needed to address the persistent inequities highlighted by these dashboards. [ABSTRACT FROM AUTHOR]

This article explores the significance of high-quality healthcare data and the challenges involved in maintaining data quality. Healthcare data possess unique characteristics such as heterogeneity, incompleteness, timeliness, longevity, privacy, and ownership. Inaccurate data can result in financial losses, increased expenses, and can impact the performance of artificial intelligence models. The article emphasizes the necessity for tailored quality assessment indicators and methods for healthcare data, as well as the implementation of quality management measures. Additional research is required to redefine quality assessment criteria and develop quantification methods specifically for healthcare data. The authors stress the importance of interdisciplinary collaboration among experts from diverse fields to ensure effective data quality assessment. [Extracted from the article]

Despite the high prevalence of cannabis consumption, there is limited information about cannabis based on scientific evidence available and targeted toward young adults, especially considering accessible language and ease of access. The present study aimed to develop the proof of concept of a chatbot for the dissemination of evidence and scientific information about cannabis, focused on a young adult audience. The proof of concept involved stages of literature review, conversation flow development, content evaluation through a panel of experts (n = 10) and usability analysis using a sample of potential users (young adults, n = 10). The chatbot developed presents information on epidemiology, toxicology, acute and chronic effects of cannabis use, information on cannabis use disorder, and the use of cannabinoids for medicinal purposes. The content evaluation through the Health Education Content Validation Instrument concluded that the tool was considered to have a good structure and content (Content Validity Index > 0,78; overall score = 9.0/10.0). The tool also proved to be functional and highly usable according to the analysis with the System Usability Scale (overall usability score = 9.2/10.0). Digital strategies such as chatbots can help in health education and scientific communication within stigmatized areas, such as the consumption of psychoactive substances. [ABSTRACT FROM AUTHOR]

Background: The mechanism for recording International Classification of Diseases (ICD) and diagnosis related groups (DRG) codes in a patient's chart is through a certified medical coder who manually reviews the medical record at the completion of an admission. High-acuity ICD codes justify DRG modifiers, indicating the need for escalated hospital resources. In this manuscript, we demonstrate that value of rules-based computer algorithms that audit for omission of administrative codes and quantifying the downstream effects with regard to financial impacts and demographic findings did not indicate significant disparities. Methods: All study data were acquired via the UCLA Department of Anesthesiology and Perioperative Medicine's Perioperative Data Warehouse. The DataMart is a structured reporting schema that contains all the relevant clinical data entered into the EPIC (EPIC Systems, Verona, WI) electronic health record. Computer algorithms were created for eighteen disease states that met criteria for DRG modifiers. Each algorithm was run against all hospital admissions with completed billing from 2019. The algorithms scanned for the existence of disease, appropriate ICD coding, and DRG modifier appropriateness. Secondarily, the potential financial impact of ICD omissions was estimated by payor class and an analysis of ICD miscoding was done by ethnicity, sex, age, and financial class. Results: Data from 34,104 hospital admissions were analyzed from January 1, 2019, to December 31, 2019. 11,520 (32.9%) hospital admissions were algorithm positive for a disease state with no corresponding ICD code. 1,990 (5.8%) admissions were potentially eligible for DRG modification/upgrade with an estimated lost revenue of $22,680,584.50. ICD code omission rates compared against reference groups (private payors, Caucasians, middle-aged patients) demonstrated significant p-values < 0.05; similarly significant p-value where demonstrated when comparing patients of opposite sexes. Conclusions: We successfully used rules-based algorithms and raw structured EHR data to identify omitted ICD codes from inpatient medical record claims. These missing ICD codes often had downstream effects such as inaccurate DRG modifiers and missed reimbursement. Embedding augmented intelligence into this problematic workflow has the potential for improvements in administrative data, but more importantly, improvements in administrative data accuracy and financial outcomes. [ABSTRACT FROM AUTHOR]

Cervical cancer, despite being preventable through primary and secondary prevention strategies, remains one of the leading causes of morbidity and mortality among women in Brazil. This study aimed to analyze the temporal, spatial, and space-time patterns of cervical cancer mortality in Brazil. An ecological study was conducted using temporal, spatial, and space-time analysis techniques, using death certificates with cervical cancer as the underlying cause or associated condition among females in Brazil from 2000 to 2021. Death certificate and population data were provided by the Department of Health Informatics of the Unified Health System (DATASUS) and the Brazilian Institute of Geography and Statistics (IBGE), respectively. A total of 123,306 deaths associated with cervical cancer among women were registered during the study period. A rising trend in mortality was detected since 2014 onwards, after 14 years of decline. Particularly, an increase in mortality was observed among the younger age groups, and in the North and Northeast regions regardless of age. Heterogeneity in the spatial distribution of cervical cancer mortality was observed, with high mortality clusters around the country, but mostly concentrated in the North and Northeast regions. These findings suggest a need and an opportunity to develop efficient and effective health policies targeting those regions and groups of women at higher risk which in turn will allow for fast and significant reductions in cervical cancer mortality in Brazil. [ABSTRACT FROM AUTHOR]

In multicentric studies, data sharing between institutions might negatively impact patient privacy or data security. An alternative is federated analysis by secure multiparty computation. This pilot study demonstrates an architecture and implementation addressing both technical challenges and legal difficulties in the particularly demanding setting of clinical research on cancer patients within the strict European regulation on patient privacy and data protection: 24 patients from LMU University Hospital in Munich, Germany, and 24 patients from Policlinico Universitario Fondazione Agostino Gemelli, Rome, Italy, were treated for adrenal gland metastasis with typically 40 Gy in 3 or 5 fractions of online-adaptive radiotherapy guided by real-time MR. High local control (21% complete remission, 27% partial remission, 40% stable disease) and low toxicity (73% reporting no toxicity) were observed. Median overall survival was 19 months. Federated analysis was found to improve clinical science through privacy-friendly evaluation of patient data in the European health data space. [ABSTRACT FROM AUTHOR]

Robust data privacy regulations hinder the exchange of healthcare data among institutions, crucial for global insights and developing generalised clinical models. Federated learning (FL) is ideal for training global models using datasets from different institutions without compromising privacy. However, disparities in electronic healthcare records (EHRs) lead to inconsistencies in ML-ready data views, making FL challenging without extensive preprocessing and information loss. These differences arise from variations in services, care standards, and record-keeping practices. This paper addresses data view heterogeneity by introducing a knowledge abstraction and filtering-based FL framework that allows FL over heterogeneous data views without manual alignment or information loss. The knowledge abstraction and filtering mechanism maps raw input representations to a unified, semantically rich shared space for effective global model training. Experiments on three healthcare datasets demonstrate the framework's effectiveness in overcoming data view heterogeneity and facilitating information sharing in a federated setup. [ABSTRACT FROM AUTHOR]

Background: The biomedical and health informatics (BMHI) fields have been advancing rapidly, a trend particularly emphasised during the recent COVID-19 pandemic, introducing innovations in BMHI. Over nearly 50 years since its establishment as a scientific discipline, BMHI has encountered several challenges, such as mishaps, delays, failures, and moments of enthusiastic expectations and notable successes. This paper focuses on reviewing the progress made in the BMHI discipline, evaluating key milestones, and discussing future challenges. Methods: To, Structured, step-by-step qualitative methodology was developed and applied, centred on gathering expert opinions and analysing trends from the literature to provide a comprehensive assessment. Experts and pioneers in the BMHI field were assigned thematic tasks based on the research question, providing critical inputs for the thematic analysis. This led to the identification of five key dimensions used to present the findings in the paper: informatics in biomedicine and healthcare, health data in Informatics, nurses in informatics, education and accreditation in health informatics, and ethical, legal, social, and security issues. Results: Each dimension is examined through recently emerging innovations, linking them directly to the future of healthcare, like the role of artificial intelligence, innovative digital health tools, the expansion of telemedicine, and the use of mobile health apps and wearable devices. The new approach of BMHI covers newly introduced clinical needs and approaches like patient-centric, remote monitoring, and precision medicine clinical approaches. Conclusions: These insights offer clear recommendations for improving education and developing experts to advance future innovations. Notably, this narrative review presents a body of knowledge essential for a deep understanding of the BMHI field from a human-centric perspective and, as such, could serve as a reference point for prospective analysis and innovation development. [ABSTRACT FROM AUTHOR]

Background: Antibiotic resistant infections cause over 700,000 deaths worldwide annually. As antimicrobial stewardship (AMS) helps minimise the emergence of antibiotic resistance resulting from inappropriate use of antibiotics in healthcare, we developed ePAMS+ (ePrescribing-based Anti-Microbial Stewardship), an ePrescribing and Medicines Administration (EPMA) system decision-support tool complemented by educational, behavioural and organisational elements. Methods: We conducted a non-randomised before-and-after feasibility trial, implementing ePAMS+ in two English hospitals using the Cerner Millennium EPMA system. Wards of several specialties were included. Patient participants were blinded to whether ePAMS+ was in use; prescribers were not. A mixed-methods evaluation aimed to establish: acceptability and usability of ePAMS+ and trial processes; feasibility of ePAMS+ implementation and quantitative outcome recording; and a Fidelity Index measuring the extent to which ePAMS+ was delivered as intended. Longitudinal semi-structured interviews of doctors, nurses and pharmacists, alongside non-participant observations, gathered qualitative data; we extracted quantitative prescribing data from the EPMA system. Normal linear modelling of the defined daily dose (DDD) of antibiotic per admission quantified its variability, to inform sample size calculations for a future trial of ePAMS+ effectiveness. Results: The research took place during the SARS-CoV-2 pandemic, from April 2021 to November 2022. 60 qualitative interviews were conducted (33 before ePAMS+ implementation, 27 after). 1,958 admissions (1,358 before ePAMS+ implementation; 600 after) included 24,884 antibiotic orders. Qualitative interviews confirmed that some aspects of ePAMS+ , its implementation and training were acceptable, while other features (e.g. enabling combinations of antibiotics to be prescribed) required further development. ePAMS+ uptake was low (28 antibiotic review records from 600 admissions; 0.047 records per admission), preventing full development of a Fidelity Index. Normal linear modelling of antibiotic DDD per admission showed a residual variance of 1.086 (log-transformed scale). Unavailability of indication data prevented measurement of some outcomes (e.g. number of antibiotic courses per indication). Conclusions: This feasibility trial encountered unforeseen circumstances due to contextual factors and a global pandemic, highlighting the need for careful adaptation of complex intervention implementations to the local setting. We identified key refinements to ePAMS+ to support its wider adoption in clinical practice, requiring further piloting before a confirmatory effectiveness trial. Trial registration: ISRCTN Registry ISRCTN13429325, 24 March 2022. [ABSTRACT FROM AUTHOR]

Background: Recently, deep learning has been increasingly applied in the field of dentistry. The aim of this study is to develop a model for the automatic segmentation, numbering, and state assessment of teeth on panoramic radiographs. Methods: We created a dual-labeled dataset on panoramic radiographs for training, incorporating both numbering and state labels. We then developed a fusion model that combines a YOLOv9-e instance segmentation model with an EfficientNetv2-l classification model. The instance segmentation model is used for tooth segmentation and numbering, whereas the classification model is used for state evaluation. The final prediction results integrate tooth position, numbering, and state information. The model's output includes result visualization and automatic report generation. Results: Precision, Recall, mAP50 (mean Average Precision), and mAP50-95 for the tooth instance segmentation task are 0.989, 0.955, 0.975, and 0.840, respectively. Precision, Recall, Specificity, and F1 Score for the tooth classification task are 0.943, 0.933, 0.985, and 0.936, respectively. Conclusions: This fusion model is the first to integrate automatic dental segmentation, numbering, and state assessment. It provides highly accurate results, including detailed visualizations and automated report generation. [ABSTRACT FROM AUTHOR]

Background: Medication reconciliation is essential for optimizing medication use. In part to promote effective medication reconciliation, the Department of Veterans Affairs (VA) invested substantial resources in health information exchange (HIE) technologies. The objectives of this qualitative study were to characterize VA clinicians' use of HIE tools for medication reconciliation in their clinical practice and to identify facilitators and barriers. Methods: We recruited inpatient and outpatient prescribers (physicians, nurse practitioners, physician assistants) and pharmacists at four geographically distinct VA medical centers for observations and interviews. Participants were observed as they interacted with HIE or medication reconciliation tools during routine work. Participants were interviewed about clinical decision-making pertaining to medication reconciliation and use of HIE tools, and about barriers and facilitators to use of the tools. Qualitative data were analyzed via inductive and deductive approaches using a priori codes. Results: A total of 63 clinicians participated. Over half (58%) were female, and the mean duration of VA clinical experience was 7 (range 0–32) years. Underlying motivators for clinicians seeking data external to their VA medical center were having new patients, current patients receiving care from an external institution, and clinicians' concerns about possible medication discrepancies among institutions. Facilitators for using HIE software were clinicians' familiarity with the HIE software, clinicians' belief that medication information would be available within HIE, and their confidence in the ability to find HIE medication-related data of interest quickly. Six overarching barriers to HIE software use for medication coordination included visual clutter and information overload within the HIE display; challenges with HIE interface navigation; lack of integration between HIE and other electronic health record interfaces, necessitating multiple logins and application switching; concerns with the dependability of HIE medication information; unfamiliarity with HIE tools; and a lack of HIE data from non-VA facilities. Conclusions: This study is believed to be the first to qualitatively characterize clinicians' HIE use with respect to medication reconciliation. Results inform recommendations to optimize HIE use for medication management activities. We expect that healthcare organizations and software vendors will be able to apply the findings to develop more effective and usable HIE information displays. [ABSTRACT FROM AUTHOR]

The rapid advancement in the field of medical imaging presents a challenge in keeping up to date with the necessary objective evaluations and optimizations for safe and effective use in clinical settings. These evaluations are traditionally done using clinical imaging trials, which while effective, pose several limitations including high costs, ethical considerations for repetitive experiments, time constraints, and lack of ground truth. To tackle these issues, virtual trials (aka in silico trials) have emerged as a promising alternative, using computational models of human subjects and imaging devices, and observer models/analysis to carry out experiments. To facilitate the widespread use of virtual trials within the medical imaging research community, a major need is to establish a common consensus framework that all can use. Based on the ongoing efforts of an AAPM Task Group (TG387), this article provides a comprehensive overview of the requirements for establishing virtual imaging trial frameworks, paving the way toward their widespread use within the medical imaging research community. These requirements include credibility, reproducibility, and accessibility. Credibility assessment involves verification, validation, uncertainty quantification, and sensitivity analysis, ensuring the accuracy and realism of computational models. A proper credibility assessment requires a clear context of use and the questions that the study is intended to objectively answer. For reproducibility and accessibility, this article highlights the need for detailed documentation, user‐friendly software packages, and standard input/output formats. Challenges in data and software sharing, including proprietary data and inconsistent file formats, are discussed. Recommended solutions to enhance accessibility include containerized environments and data‐sharing hubs, along with following standards such as CDISC (Clinical Data Interchange Standards Consortium). By addressing challenges associated with credibility, reproducibility, and accessibility, virtual imaging trials can be positioned as a powerful and inclusive resource, advancing medical imaging innovation and regulatory science. [ABSTRACT FROM AUTHOR]

Introduction: This study aimed to investigate how shared decision‐making (SDM) and the use of different types of outcome information are applied in routine care management for people with multiple sclerosis (MS) in an academic outpatient clinic. Methods: This qualitative study used the following: (a) observations of clinical encounters (N = 23) between patients and healthcare professionals (HCPs), (b) interviews with those patients (N = 17) and (c) interviews with those HCPs (N = 7). HCPs were not trained in SDM before the study. Audio recordings were transcribed literally. Transcriptions were analysed using qualitative thematic analysis. Results: Outcome information was hardly discussed with patients, apart from clinical outcome information at an individual level, such as MRI or lab results. This use of clinical outcome information did not automatically lead to a process of SDM. HCPs tended to implicitly present choices to patients after signalling and discussing 'problems'. In the interviews, patients indicated that they tended to consent to the advice given by HCPs and to prefer not too much change in treatment plans. However, they also emphasized the importance of being informed about available options with benefits and harms. We observed multiple discussions about patients' preferences, especially related to patients' experiences and priorities. Conclusions: Overall, SDM and the use of different types of outcome information did not seem to be enacted in routine care management for people with MS, mostly because choices were not explicitly mentioned or discussed. However, discussions about patients' experiences and priorities did take place. Training HCPs further and developing patient information seem reasonable steps to proceed. Patient or Public Contribution: People with MS contributed as research participants and provided us with their experiences in interviews. Furthermore, representatives of two patient organizations contributed to the study by reviewing the interview protocol for people with MS. [ABSTRACT FROM AUTHOR]

Background and Objective: The data modernization initiative (DMI) is a multi‐year, multi‐billion‐dollar endeavor toward a robust public health information infrastructure. The various DMI projects (interoperability, analytics, workforce, governance) present an opportunity for a learning health system (LHS) framework in public health. The objective is to share an academic‐practice partnership model between the University of Minnesota (UMN) and the Minnesota Department of Health (MDH) in advancing public health informatics (PHI) and its relationship to an LHS model. Methods: The UMN‐MDH partnership was conceptualized in 2018 as a 1‐year pilot with annual renewals through a time/cost‐sharing faculty position with PHI expertise. The partnership focus was decided based on MDH's needs and mutual interests, with the core collaborating faculty (SR) being an embedded researcher at MDH. Responsibilities included supporting electronic case reporting (eCR), interoperability projects, and assisting MDH staff with PHI presentations/publications. The partnership has expanded to PHI workforce development through a national grant and now includes an interest in applying the LHS framework to MDH‐DMI work. Results: The MDH‐DMI team has embarked upon 13 projects for assessment through an LHS approach: systems interoperability projects between MDH and healthcare/local public health (n = 6); systems modernization for MDH programs (n = 5); informatics workforce development (n = 1); and program governance (n = 1). Each project has been evaluated and/or has current/future assessment plans to synthesize learnings and create a feedback loop for iterative improvement. The partnership has been mutually beneficial as it met agreed upon metrics across both institutions. The program's productivity is showcased with shared authorship in 10 peer‐reviewed proceedings/publications, 22 presentations and 16 posters across local/national conferences. Conclusion: The current case report of the UMN‐MDH partnership is a relatively recent exemplar to support tangible LHS demonstration in public health. Building LHS momentum at MDH and other public health entities will require LHS champion(s) and continued academic collaboration. [ABSTRACT FROM AUTHOR]

Introduction: This study presents two novel concepts for standardizing electronic health records (EHR)‐based public health surveillance through utilization of existing informatics methods and data platforms. Methods: Drawing from the collective experience in applied epidemiology, health services research and health informatics, the author presents a vision for an alternative path to public health surveillance by repurposing existing tools and resources, such as (1) computable phenotypes which have already been created and validated for a variety of chronic diseases of interest to public health and (2) large data platforms/collaboratives, such as All of Us Research Program and National COVID Cohort Collaborative. Opportunities and challenges are discussed regarding EHR‐based chronic disease surveillance, as well as the concept of phenotype definitions and large data platforms reuse for public health needs. Results/Framework: Reusing of computable phenotypes for EHR‐based public health surveillance would require secure data platforms and nationally representative data. Standardization metrics for reuse of previously developed and validated computable phenotypes are also necessary and are currently being developed by the author. This study presents a reimagined Learning Health System framework by incorporating Public Health and two novel concept sets of solutions into the healthcare ecosystem. Conclusion/Next Steps: Alternative approaches to limited resources and current infrastructure of the US Public Health System, especially as applied to disease surveillance, are needed and may be possible when repurposing the resources and methodologies across the Learning Health System. [ABSTRACT FROM AUTHOR]

People are becoming more reliant on social media networks to express their opinions about various topics and obtain health information. The study is intended to explore and analyse the sentiments of Indian people related to Covid-19 vaccines as well as to visualise the top most frequently occurring terms individuals have used to communicate their ideas on Twitter about Covid-19 vaccines in India. The Tweet Archiver was used to retrieve the Tweets against 'Covid19vaccine' and 'Coronavirusvaccine' hashtags for the period of 2 months 18 days (4 January 2021–22 March 2021). After collecting data, the Orange software and VOSviewer were used for further analysis. The Tweets were posted across the country, with an immense contribution from Maharashtra (223, 15.58%), followed by Delhi (220, 15.37%) and Tamil Nadu (73, 5.10%). The majority (639, 44.65%) of the Tweets reflect positive sentiments, followed by neutral (521, 38.50%) and negative (241, 16.84%) sentiments, respectively. This signifies that most Twitter users have a favourable opinion towards Covid vaccines in India. Based on the relevance score of the words, the words 'Delhi heart', 'Lung institute', 'Gift', 'Unite2fightcorona', and 'Covid-19 Vaccine' are the leading words appearing in Tweets. The study illustrates the sentiments of the Indian people towards 'Covid-19 vaccines', gains some insights into overall public communication about the topic and complements the existing literature. It can assist health policymakers and administrators in better understanding the polarity (positive, negative, and neutral) of Tweets about Covid-19 vaccines on Twitter to raise public awareness about health concerns and misinformation about the vaccine. [ABSTRACT FROM AUTHOR]

This article centers around the development and analysis of machine learning (ML) and deep learning models aimed at enhancing diabetes diagnosis. In the swiftly evolving landscape of data technologies, it becomes crucial to explore the applications of these methods for accurate predictions and improved medical decision-making. Our research encompasses diverse datasets, leveraging state-of-the-art algorithms and technologies for model training and testing. The primary emphasis lies in evaluating the accuracy, sensitivity, and specificity of models within the realm of diabetes diagnosis. The study results reveal significant advancements in disease prediction, underscoring the potential of ML and deep learning in medical applications. This work introduces fresh perspectives on the utilization of computational methods in healthcare and serves as a foundation for prospective research in this domain. [ABSTRACT FROM AUTHOR]

The article discusses the evolution of the pharmacy industry, highlighting the shift from being solely dispensers of medications to becoming clinical experts focused on improving patient outcomes. Pharmacists have expanded their roles to include evaluating medication appropriateness, improving adherence, providing health services, and managing medications. The industry emphasizes the importance of empowering pharmacists with data to proactively improve medication safety and quality outcomes, but faces challenges related to data access and use. Overall, the article underscores the need for industry support, training, and user-friendly infrastructure to continue advancing medication safety and quality improvements. [Extracted from the article]

The rapid advancement of artificial intelligence (AI) in healthcare has the potential to revolutionize the global healthcare sector and medicine in general. However, integrating AI technologies in healthcare requires access to large amounts of personal health-related data (HRD), which raises concerns regarding confidential personal information considering unregulated and not transparent data ownership. Setting up the patient's welfare as an unquestionable principle, this commentary explores the various ethical aspects of using HRD in AI applications, focusing on informed consent, data ownership, data sharing, financial considerations, accountability, and ethical standards. Three models of potential collaboration between AI-specializing firms and healthcare providers are evaluated: the commercial model, the equitable profit-sharing model, and the public-funded non-profit model. Each model has its advantages and challenges, necessitating a careful balance between ethical considerations, financial implications, and technological advancements. Policymakers and healthcare regulators are urged to establish transparent legislation to safeguard patient privacy, ensure informed consent, and promote the responsible use of HRD in AI applications. This commentary emphasizes the importance of addressing ethical issues to protect basic patient rights, foster responsible collaborations, and ensure the ethical use of health-related data in AI-based healthcare applications. While the coexistence of regulated AI and healthcare professionals is inevitable for validating the cost-effectiveness of AI use in healthcare economics, the transparency of HRD sources is deemed of utmost importance in the best interest of the patient. [ABSTRACT FROM AUTHOR]

This study investigates the utility of Google Trends and Google Search data in retrospectively analyzing the Flint Water Crisis, a significant public health event. By examining keywords relevant to the crisis, such as "lead," "bottled water," "water filters," "pneumonia," and "Legionnaires' Disease," we aimed to uncover patterns in public awareness and response during a public crisis and explore how such awareness and responses could potentially aid in reducing the risk of similar crises in the future. Our analysis reveals a clear correlation between search frequencies and the crisis timeline, with spikes in search terms corresponding to key events. This suggests that such data can serve as a valuable tool for understanding public sentiment and behavior in the face of environmental disasters. The research underscores the potential of "Big Data," led by search engines and social media platforms, in shaping public policy and informed decision-making. However, it also addresses the limitations and challenges in using these data sources, including issues of data consistency, replicability, and the influence of sociocultural contexts on search behaviors. The study advocates for the combined use of Google Trends and Google Search data, complemented by other datasets, for a more comprehensive understanding of public engagement in environmental crises. This work contributes to the growing field of infodemiology, emphasizing the importance of big data analysis in environmental science and public health research. [ABSTRACT FROM AUTHOR]

Most clinical information is encoded as free text, not accessible for quantitative analysis. This study presents an open-source pipeline using the local large language model (LLM) "Llama 2" to extract quantitative information from clinical text and evaluates its performance in identifying features of decompensated liver cirrhosis. The LLM identified five key clinical features in a zero- and one-shot manner from 500 patient medical histories in the MIMIC IV dataset. We compared LLMs of three sizes and various prompt engineering approaches, with predictions compared against ground truth from three blinded medical experts. Our pipeline achieved high accuracy, detecting liver cirrhosis with 100% sensitivity and 96% specificity. High sensitivities and specificities were also yielded for detecting ascites (95%, 95%), confusion (76%, 94%), abdominal pain (84%, 97%), and shortness of breath (87%, 97%) using the 70 billion parameter model, which outperformed smaller versions. Our study successfully demonstrates the capability of locally deployed LLMs to extract clinical information from free text with low hardware requirements. [ABSTRACT FROM AUTHOR]

This research letter explores the concept of "clinical momentum" in the care of older adults with advanced dementia. Clinical momentum refers to the tendency for interventions to be performed near the end of life, often resulting in excessive treatment. The study specifically focuses on the use of feeding tubes in patients with advanced dementia as an example of overtreatment. The researchers conducted a retrospective case-control study using electronic health records to identify patients with dementia who received a permanent feeding tube and compared them to controls who did not receive a feeding tube. The study aims to identify markers of clinical momentum in the medical records. The findings indicate that patients with advanced dementia who received a permanent feeding tube had longer hospital stays and more events such as discussions about goals of care and consultations for palliative care. The study suggests that prolonged exposure to a healthcare system that prioritizes interventions for isolated problems can result in care that does not align with guidelines. However, it is important to note that the study has limitations, including a small and nondiverse sample. [Extracted from the article]

The field of medical informatics has been significantly transformed in recent years with the emergence of Natural Language Understanding (NLU) and Large Language Models (LLM), providing new opportunities for innovative patient care solutions. This study aims to evaluate the effectiveness of publicly available LLMs as symptom checkers for cardiological diseases by comparing their diagnostic capabilities in real disease cases. We employed a set of 9 models, including ChatGPT-4, OpenSource models, Google PaLM 2, and Meta's LLaMA, to assess their diagnostic accuracy, reliability, and safety across various clinical scenarios. Our methodology involved presenting these LLMs with symptom descriptions and test results in Spanish, requiring them to provide specialist diagnoses and recommendations in English. This approach allowed us to compare the performance of each model, highlighting their respective strengths and limitations in a healthcare context. The results revealed varying levels of accuracy, precision, and sensitivity among the models, demonstrating the potential of LLMs to enhance medical education and patient care. By analysing the capabilities of each model, our study contributes to a deeper understanding of artificial intelligence's role in medical diagnosis. We argue for the strategic implementation of LLMs in healthcare, emphasizing the importance of balancing sensitivity and realism to optimize patient outcomes. [ABSTRACT FROM AUTHOR]

Objective: To conduct a comprehensive bibliometric analysis of the application of artificial intelligence (AI) in Rare diseases (RDs), with a focus on analyzing publication output, identifying leading contributors by country, assessing the extent of international collaboration, tracking the emergence of research hotspots, and detecting trends through keyword bursts. Methods: In this bibliometric study, we identified and retrieved publications on AI applications in RDs spanning 2003 to 2023 from the Web of Science (WoS). We conducted a global research landscape analysis and utilized CiteSpace to perform keyword clustering and burst detection in this field. Results: A total of 1501 publications were included in this study. The evolution of AI applications in RDs progressed through three stages: the start-up period (2003–2010), the steady development period (2011–2018), and the accelerated growth period (2019–2023), reflecting this field's increasing importance and impact at the time of the study. These studies originated from 85 countries, with the United States as the leading contributor. "Mutation", "Diagnosis", and "Management" were the top three keywords with high frequency. Keyword clustering analysis identified gene identification, effective management, and personalized treatment as three primary research areas of AI applications in RDs. Furthermore, the keyword burst detection indicated a growing interest in the areas of "biomarker", "predictive model", and "data mining", highlighting their potential to shape future research directions. Conclusions: Over two decades, research on the AI applications in RDs has made remarkable progress and shown promising results in the development. Advancing international transboundary cooperation is essential moving forward. Utilizing AI will play a more crucial role across the spectrum of RDs management, encompassing rapid diagnosis, personalized treatment, drug development, data integration and sharing, and continuous monitoring and care. [ABSTRACT FROM AUTHOR]

Background: Hospitalizations for exacerbations of congestive heart failure (CHF), chronic obstructive pulmonary disease (COPD) and diabetic ketoacidosis (DKA) are costly in the United States. The purpose of this study was to predict in-hospital charges for each condition using machine learning (ML) models. Results: We conducted a retrospective cohort study on national discharge records of hospitalized adult patients from January 1st, 2016, to December 31st, 2019. We constructed six ML models (linear regression, ridge regression, support vector machine, random forest, gradient boosting and extreme gradient boosting) to predict total in-hospital cost for admission for each condition. Our models had good predictive performance, with testing R-squared values of 0.701-0.750 (mean of 0.713) for CHF; 0.694-0.724 (mean 0.709) for COPD; and 0.615-0.729 (mean 0.694) for DKA. We identified important key features driving costs, including patient age, length of stay, number of procedures, and elective/nonelective admission. Conclusions: ML methods may be used to accurately predict costs and identify drivers of high cost for COPD exacerbations, CHF exacerbations and DKA. Overall, our findings may inform future studies that seek to decrease the underlying high patient costs for these conditions. [ABSTRACT FROM AUTHOR]