BACKGROUND: Clinical notes contain contextualized information beyond structured data related to patients\' past and current health status.
OBJECTIVE: This study aimed to design a multimodal deep learning approach to improve the evaluation precision of hospital outcomes for heart failure (HF) using admission clinical notes and easily collected tabular data.
METHODS: Data for the development and validation of the multimodal model were retrospectively derived from 3 open-access US databases, including the Medical Information Mart for Intensive Care III v1.4 (MIMIC-III) and MIMIC-IV v1.0, collected from a teaching hospital from 2001 to 2019, and the eICU Collaborative Research Database v1.2, collected from 208 hospitals from 2014 to 2015. The study cohorts consisted of all patients with critical HF. The clinical notes, including chief complaint, history of present illness, physical examination, medical history, and admission medication, as well as clinical variables recorded in electronic health records, were analyzed. We developed a deep learning mortality prediction model for in-hospital patients, which underwent complete internal, prospective, and external evaluation. The Integrated Gradients and SHapley Additive exPlanations (SHAP) methods were used to analyze the importance of risk factors.
RESULTS: The study included 9989 (16.4%) patients in the development set, 2497 (14.1%) patients in the internal validation set, 1896 (18.3%) in the prospective validation set, and 7432 (15%) patients in the external validation set. The area under the receiver operating characteristic curve of the models was 0.838 (95% CI 0.827-0.851), 0.849 (95% CI 0.841-0.856), and 0.767 (95% CI 0.762-0.772), for the internal, prospective, and external validation sets, respectively. The area under the receiver operating characteristic curve of the multimodal model outperformed that of the unimodal models in all test sets, and tabular data contributed to higher discrimination. The medical history and physical examination were more useful than other factors in early assessments.
CONCLUSIONS: The multimodal deep learning model for combining admission notes and clinical tabular data showed promising efficacy as a potentially novel method in evaluating the risk of mortality in patients with HF, providing more accurate and timely decision support.

BACKGROUND: Cohen syndrome (CS) is a rare autosomal recessive inherited condition characterized by pathological changes affecting multiple systems. The extensive clinical variability associated with CS poses a significant diagnostic challenge. Additionally, there is limited documentation on the co-occurrence of CS with psychiatric symptoms.
METHODS: We report a case of a 30-year-old patient exhibiting characteristic physical features and psychiatric symptoms. Whole exome sequencing identified two heterozygous variants, a nonsense variation c.4336 C > T and a missense mutation c.4729G > A. Integrating clinical manifestations with genetic test results, we established the diagnosis of CS combined with psychiatric symptoms.
CONCLUSIONS: This case introduces a novel missense variant as a candidate in the expanding array of VPS13B pathogenic variants. Its clinical significance remains unknown, and further investigation may broaden the spectrum of pathogenic variants associated with the VPS13B gene. Early diagnosis of CS is crucial for the prognosis of young children and holds significant importance for their families.

Over the course of history global population has witnessed deterioration of unprecedented scale caused by infectious transmission. The necessity to mitigate the infectious flow requires the launch of a well-directed and inclusive set of efforts. Motivated by the urge for continuous improvement in existing schemes, this article aims at the encapsulation of the dynamics of the spread of infectious diseases. The objectives are served by the launch of the infectious disease model. Moreover, an optimal control strategy is introduced to ensure the incorporation of the most feasible health interventions to reduce the number of infected individuals. The outcomes of the research are facilitated by stratifying the population into five compartments that are susceptible class, acute infected class, chronic infected class, recovered class, and vaccinated class. The optimal control strategy is formulated by incorporating specific control variables namely, awareness about medication, isolation, ventilation, vaccination rates, and quarantine level. The developed model is validated by proving the pivotal delicacies such as positivity, invariant region, reproduction number, stability, and sensitivity analysis. The legitimacy of the proposed model is delineated through the detailed sensitivity analysis along with the documentation of local and global features in a comprehensive manner. The maximum sensitivity index parameters are disease transmission and people moved from acute stages into chronic stages whose value is (0.439, 1) increase in parameter by 10 percent would increase the threshold quantity by (4.39, 1). Under the condition of a stable system, we witnessed an inverse relationship between susceptible class and time. Moreover, to assist the gain of the fundamental aim of this research, we take the control variables as time-dependent and obtain the optimal control strategy to minimize infected populations and to maximize the recovered population, simultaneously. The objectives are attained by the employment of the Pontryagin maximum principle. Furthermore, the efficacy of the usual health interventions such as quarantine, face mask usage, and hand sanitation are also noticed. The effectiveness of the suggested control plan is explained by using numerical evaluation. The advantages of the new strategy are highlighted in the article.

BACKGROUND: Complete documentation of critical care events in the accident and emergency department (AED) is essential. Due to the fast-paced and complex nature of resuscitation cases, missing data is a common issue during emergency situations.
OBJECTIVE: This study aimed to evaluate the impact of a tablet-based resuscitation record on documentation completeness during medical resuscitations and nurses\' perceptions of the use of the tablet app.
METHODS: A mixed methods approach was adopted. To collect quantitative data, randomized retrospective reviews of paper-based resuscitation records before implementation of the tablet (Pre-App Paper; n=176), paper-based resuscitation records after implementation of the tablet (Post-App Paper; n=176), and electronic tablet-based resuscitation records (Post-App Electronic; n=176) using a documentation completeness checklist were conducted. The checklist was validated by 4 experts in the emergency medicine field. The content validity index (CVI) was calculated using the scale CVI (S-CVI). The universal agreement S-CVI was 0.822, and the average S-CVI was 0.939. The checklist consisted of the following 5 domains: basic information, vital signs, procedures, investigations, and medications. To collect qualitative data, nurses\' perceptions of the app for electronic resuscitation documentation were obtained using individual interviews. Reporting of the qualitative data was guided by Consolidated Criteria for Reporting Qualitative Studies (COREQ) to enhance rigor.
RESULTS: A significantly higher documentation rate in all 5 domains (ie, basic information, vital signs, procedures, investigations, and medications) was present with Post-App Electronic than with Post-App Paper, but there were no significant differences in the 5 domains between Pre-App Paper and Post-App Paper. The qualitative analysis resulted in main categories of \"advantages of tablet-based documentation of resuscitation records,\" \"challenges with tablet-based documentation of resuscitation records,\" and \"areas for improvement of tablet-based resuscitation records.\"
CONCLUSIONS: This study demonstrated that higher documentation completion rates are achieved with electronic tablet-based resuscitation records than with traditional paper records. During the transition period, the nurse documenters faced general problems with resuscitation documentation such as multitasking and unique challenges such as software updates and a need to familiarize themselves with the app\'s layout. Automation should be considered during future app development to improve documentation and redistribute more time for patient care. Nurses should continue to provide feedback on the app\'s usability and functionality during app refinement to ensure a successful transition and future development of electronic documentation records.

BACKGROUND: Massive hiatal hernias may result in extraoesophageal symptoms, including iron-deficiency anaemia. However, the role played by hiatal hernias in iron-deficiency anaemia is not clearly understood. We examined the prevalence of anaemia in patients with massive hiatal hernias and the frequency of anaemia resolution after laparoscopic hiatal hernia repair at long term follow-up.
METHODS: Patients who underwent laparoscopic hiatal hernia repair from June 2008 to June 2019 were enrolled in this study. We collected the patients\' demographic and clinical data from their medical records, and compared the pre-surgical and post-surgical findings (at 1 week and 3 months post-surgery). All patients with adequate documentation underwent post-surgical follow-up to evaluate improvements in clinical symptoms and signs.
RESULTS: A total of 126 patients with massive hiatal hernias underwent laparoscopic hiatal hernia repair. Of these, 35 (27.8%) had iron-deficiency anaemia. Anaemia was resolution in all the patients and they had significantly reduced GERD-Q scores at 3 months postoperatively (P<0.01) .The mean follow-up period was 60 months. Iron-deficiency anaemia resolution after hiatal hernia repair was achieved in 93.9% of the patients.
CONCLUSIONS: Anaemia is common in patients with massive hiatal hernias, and most of our patients were symptomatic because of their anaemia. Moreover, in patients with massive hiatal hernias, iron-deficiency anaemia resolution is likely after laparoscopic hiatal hernia repair.

Automatic radiology report generation has the potential to alert inexperienced radiologists to misdiagnoses or missed diagnoses and improve healthcare delivery efficiency by reducing the documentation workload of radiologists. Motivated by the continuous development of automatic image captioning, more and more deep learning methods have been proposed for automatic radiology report generation. However, the visual and textual data bias problem still face many challenges in the medical domain. Additionally, do not integrate medical knowledge, ignoring the mutual influences between medical findings, and abundant unlabeled medical images influence the accuracy of generating report. In this paper, we propose a Medical Knowledge with Contrastive Learning model (MKCL) to enhance radiology report generation. The proposed model MKCL uses IU Medical Knowledge Graph (IU-MKG) to mine the relationship among medical findings and improve the accuracy of identifying positive diseases findings from radiologic medical images. In particular, we design Knowledge Enhanced Attention (KEA), which integrates the IU-MKG and the extracted chest radiological visual features to alleviate textual data bias. Meanwhile, this paper leverages supervised contrastive learning to relieve radiographic medical images which have not been labeled, and identify abnormalities from images. Experimental results on the public dataset IU X-ray show that our proposed model MKCL outperforms other state-of-the-art report generation methods. Ablation studies also demonstrate that IU medical knowledge graph module and supervised contrastive learning module enhance the ability of the model to detect the abnormal parts and accurately describe the abnormal findings. The source code is available at: https://github.com/Eleanorhxd/MKCL.

To boost the handful of nutrient-dense individuals in the societal structure, adequate health care documentation and comprehension are permitted. This will strengthen and optimize the well-being of the community, particularly the girls and women of the community that are welcoming the new generation. In this article, we extensively explored a deterministic-stochastic malnutrition model involving nonlinear perturbation via piecewise fractional operators techniques. This novel concept leads us to analyze and predict the process from the beginning to the end of the well-being growth, as it offers the possibility to observe many behaviors from cross over to stochastic processes. Moreover, the piecewise differential operators, which can be constructed with operators such as classical, Caputo, Caputo-Fabrizio, Atangana-Baleanu and stochastic derivative. The threshold parameter is developed and the role of malnutrition in society is examined. Through a rigorous analysis, we first demonstrated that the stochastic model\'s solution is positive and global. Then, using appropriate stochastic Lyapunov candidates, we examined whether the stochastic system acknowledges a unique ergodic stationary distribution. The objective of this investigation is to design a nutritional deficiency in pregnant women using a piecewise fractional differential equation scheme. We examined multiple options and outlined numerical methods of coping with problems. To exemplify the effectiveness of the suggested concept, graphical conclusions, including chaotic and random perturbation patterns, are supplied. Consequently, fractional calculus\' innovative aspects provide more powerful and flexible layouts, enabling us to more effectively adapt to the system dynamics tendencies of real-world representations. This has opened new doors to readers in different disciplines and enabled them to capture different behaviors at different time intervals.

暂无摘要。

ChatGPT is receiving increasing attention and has a variety of application scenarios in clinical practice. In clinical decision support, ChatGPT has been used to generate accurate differential diagnosis lists, support clinical decision-making, optimize clinical decision support, and provide insights for cancer screening decisions. In addition, ChatGPT has been used for intelligent question-answering to provide reliable information about diseases and medical queries. In terms of medical documentation, ChatGPT has proven effective in generating patient clinical letters, radiology reports, medical notes, and discharge summaries, improving efficiency and accuracy for health care providers. Future research directions include real-time monitoring and predictive analytics, precision medicine and personalized treatment, the role of ChatGPT in telemedicine and remote health care, and integration with existing health care systems. Overall, ChatGPT is a valuable tool that complements the expertise of health care providers and improves clinical decision-making and patient care. However, ChatGPT is a double-edged sword. We need to carefully consider and study the benefits and potential dangers of ChatGPT. In this viewpoint, we discuss recent advances in ChatGPT research in clinical practice and suggest possible risks and challenges of using ChatGPT in clinical practice. It will help guide and support future artificial intelligence research similar to ChatGPT in health.

Medication safety is a significant concern in healthcare. Research on medication safety for older adults has taken a broad approach, resulting in a range of proposals. At this juncture, it is necessary to identify the main contributors and establish the current developmental status of the principal research topics.
This study sets out to summarize the state-of-the-art in medication safety for older adults, identifying significant achievements, key topics, and emerging trends.
The Web of Science Core Collection (WOSCC) database was searched for relevant documentation over the interval 1st January 2000 to 31st December 2021. Annual outputs and citations were identified from the WOS citation reports. CiteSpace and VOSviewer were adopted for bibliometric analysis and visualization that included the distribution of countries/regions, organizations, authors and journals, and an analysis of co-cited references and keywords.
A total of 1,638 documents were retrieved for bibliometric analysis, yielding 34.29 citations per document. Publications have increased over the past two decades, reaching 177 outputs in 2019. Our database encompasses 71 countries/regions, 2,347 organizations, and 7,040 authors. The United States ranks first in terms of scientific activity with 604 publications (36.87%). We have identified the University of Sydney as the most prolific organization (53 publications). J. T. Hanlon, J. H. Gurwitz, D. O\'Mahony, and G. Onder are the most influential researchers in terms of publications and citations. The Journal of the American Geriatrics Society ranks first with 89 (5.43%) papers. In terms of major research directions, three topics have been identified from co-cited reference and keyword analysis: (1) estimation of the prevalence and variables associated with polypharmacy and potentially inappropriate medication; (2) analysis of interventions involving pharmacists and the associated impact; (3) patient experience and perception associated with medication use or pharmaceutical care.
Research on medication safety for older adults has progressed significantly over the past two decades. The United States, in particular, has made important contributions to this field. Polypharmacy and potentially inappropriate medication use, interventions involving pharmacists, patient experience and perception represent the current focus of research. Our findings suggest that these directions will continue as research hotspots in the future.