The integration of artificial intelligence (AI) into medical education has the potential to revolutionize the way students learn about biomedical sciences. Large language models, such as ChatGPT, can serve as virtual teaching assistants, providing students with detailed and relevant information and perhaps eventually interactive simulations. ChatGPT has the potential to increase student engagement and enhance student learning, though research is needed to confirm this. The challenges and limitations of ChatGPT must also be considered, including ethical issues and potentially harmful effects. It is crucial for medical educators to keep pace with technology's rapidly changing landscape and consider the implications for curriculum design, assessment strategies, and teaching methods. Continued research and evaluation are necessary to ensure the optimal integration of AI‐based learning tools into medical education.
Omolola Akinola, Akintunde Akinola, Bairat Oyekan
et al.
The current period of medicine using digital technology for patient care presents a new level of integration of monitoring devices with the cloud computing environment that enables the collection, storage and access to data in ways that were never possible earlier. As the obvious part of this development, it is worth noting that the objective of such innovation is mostly on the integrity of data, provenance and security. Data integrity from as well as security of the Internet connected healthcare devices should be assured in the first place to keep patient safety and protect data privacy along with improve data-based decision-making. The centralized system and crowded nature of the current equipment are susceptible to single point of failure, data breach and potential manipulations of data, which raise questions and create doubts with regards data management processes pertaining to medical device systems. This work is addressed to the analysis of a novel security system based on blockchain that guarantees the implementation of a high performance with the solution of two medical device integrity and provenance safety issues in the cloud ecosystem. Fundamentally differentiating from the centralized systems that exist today, blockchain technology that is based on distributed database architectures, immutable logs, and consensus mechanisms provides for a new way to bring reliability and traceability to the entire medical device data chain. The suggested procedure is based on properties of blockchain technology. Such a solution can help to provide a clear and secure audit trail for medical devices. Storing, securing and accessing the device data can be carried out credibly, maintaining these data’s integrity and provenance. Ultimately, the solution, rely on the implementation of smart contracts, cryptocurrency processes, and the confidentiality and privacy of data, can be the answer which make up the practice of secure data sharing, data accessing and complying with regulations. The journal creates a modular system combining Medical devices, a cloud platform, and Blockchain solution. The architecture is intended to display the blockchain network's essential components, data validation and access control, and secure data storage mechanisms. Furthermore, the recommended solution implies state-of- the-art security tools, such as data encryption, access control, and abidance by regulatory systems, including HIPAA and GDPR. Implementation of an actual scenario of the proof-of-concept and performance evaluation are done to show the efficiency and performance of the blockchain-based solution provided. The results suggest that the proposed solution can establish the data reliability level, record all the various versions of modifications, and strengthen the security and transparency of medical device data processing in cloud computing. Through the exploration of the applications of blockchain for medical data management that this study proposes, we are laying the foundations of a future healthcare environment, which is expected to be more secure and trustworthy, where the sensor data of medical devices can be reliably controlled and accessed without jeopardizing the patient's safety or data privacy. To a great extent, the suggested solution can contribute to building trust in the digital tools utilized in health care, leading to more well-informed clinical decisions and ultimately improving the patients' results.
Abstract Background The P53-mutated Hepatocellular Carcinoma (HCC) is an aggressive variant associated with vascular endothelial growth factor (VEGF) overexpression and increased microvascular density. This study aimed to develop an MRI-based deep learning model for predicting P53-mutated HCC. Methods A total of 312 HCC patients who underwent gadolinium-enhanced MRI and were pathologically confirmed between January 2018 and December 2023 were retrospectively enrolled. Participants were randomly divided into training and test dataset at an 8:2 ratio. We developed an EfficientNetV2-based deep learning model, constructing arterial phase (AP) model, portal venous phase (VP), T2-weighted imaging (T2WI), hepatobiliary phase (HBP) single-sequence model, and combined models to predict P53 mutation status. Model performance was evaluated using the area under the curve (AUC), accuracy, sensitivity, specificity, precision, and F1 score as metrics. Differences in AUC values were compared using Delong’s test. Results A total of 312 pathologically confirmed HCC patients (age: 56 ± 9 years; male = 240) were included, with a training dataset (n = 249) and test dataset (n = 63).Among single-sequence models, the HBP model demonstrated superior diagnostic performance (AUC = 0.715) compared to T2WI, AP, and VP models. The multiphase combined model (T2WI + AP + VP) significantly outperformed single-sequence models, achieving AUCs of 0.982 (95% CI: 0.959–1.000) in the training dataset and 0.914 (95% CI: 0.819–1.000) in the test dataset. However, incorporating the HBP sequence into the combined model (T2WI + AP + VP + HBP) did not further improve diagnostic performance (P > 0.05). Advances in knowledge The combined model incorporating AP, VP, T2WI, and HBP sequences demonstrated numerically highest performance in predicting P53-mutated HCC.
Background Emotional disorders are common in children and young people and can significantly impair their quality of life. Evidence-based treatments require a timely and appropriate diagnosis. The utility of standardised diagnostic assessment tools may aid the detection of emotional disorders, but there is limited evidence of their clinical value. Objectives To assess the clinical effectiveness and cost effectiveness of a standardised diagnostic assessment for children and young people with emotional difficulties referred to Child and Adolescent Mental Health Services. A nested qualitative process evaluation aimed to identify the barriers and facilitators to using a standardised diagnostic assessment tool in Child and Adolescent Mental Health Services. Design A United Kingdom, multicentre, two-arm, parallel-group randomised controlled trial with a nested qualitative process evaluation. Setting Eight National Health Service Trusts providing multidisciplinary specialist Child and Adolescent Mental Health Services. Participants Children and young people aged 5–17 years with emotional difficulties referred to Child and Adolescent Mental Health Services, excluding emergency/urgent referrals that required an expedited assessment. In the qualitative process evaluation, 15 young people aged 16–17 years, 38 parents/carers and 56 healthcare professionals participated in semistructured interviews. Interventions Participants were randomly assigned (1 : 1) following referral receipt to intervention (the development and well-being assessment) and usual care, or usual care only. Main outcome measures Primary outcome was a clinician-made diagnosis decision about the presence of an emotional disorder within 12 months of randomisation, collected from Child and Adolescent Mental Health Services clinical records. Secondary outcomes collected from clinical records included referral acceptance, time to offer and start treatment/interventions and discharge. Data were also self-reported from participants through online questionnaires at baseline, 6 and 12 months post randomisation, and the cost effectiveness of the intervention was investigated. Results One thousand two hundred and twenty-five (1225) children and young people were randomly assigned (1 : 1) to study groups between 27 August 2019 and 17 October 2021; 615 were assigned to the intervention and 610 were assigned to the control group. Adherence to the intervention (full/partial completion of the development and well-being assessment) was 80% (494/615). At 12 months, 68 (11%) participants in the intervention group received an emotional disorder diagnosis versus 72 (12%) in the control group [adjusted risk ratio 0.94 (95% confidence interval 0.70 to 1.28); p = 0.71]. Child and Adolescent Mental Health Services acceptance of the index referral [intervention 277 (45%) vs. control 262 (43%); risk ratio: 1.06 (95% confidence interval: 0.94 to 1.19)] or any referral by 18 months [intervention 374 (61%) vs. control 352 (58%); risk ratio: 1.06 (95% confidence interval: 0.97 to 1.16)] was similar between groups. There was no evidence of any differences between groups for any other secondary outcomes. The qualitative nested process evaluation identified a number of barriers and facilitators to the use of the development and well-being assessment during the trial, particularly at the assessment and diagnosis stages of the Child and Adolescent Mental Health Services pathway. Limitations It was not possible to mask participants, clinicians or site researchers collecting source data to treatment allocation. Conclusions We found no evidence that completion of the development and well-being assessment aided the detection of emotional disorders in this study. Using the development and well-being assessment in this way cannot be recommended for clinical practice. Future research To determine longer-term service use outcomes and to investigate whether receipt of a clinical diagnosis makes a difference to clinical outcomes and care/intervention receipt. Funding This synopsis presents independent research funded by the National Institute for Health and Care Research (NIHR) Health Technology Assessment programme as award number 16/96/09.
Plain language summary Emotional difficulties are common in children and young people, and many may be referred to Child and Adolescent Mental Health Services. Referrals are sometimes rejected because of insufficient information. Even if the referral is accepted, a clinical diagnosis is often not reached. A correct diagnosis is vital so that the right help can be offered. We investigated whether a standardised online information-gathering package (development and well-being assessment) helps with the assessment and diagnosis process in Child and Adolescent Mental Health Services. We invited children and young people and their families, following a routine (non-urgent) referral into Child and Adolescent Mental Health Services, from eight National Health Services Trusts across England. One thousand two hundred and twenty-five (1225) families took part – half received usual care (control group), and half received usual care and were also asked to complete the development and well-being assessment (development and well-being assessment group). Families also completed questionnaires about the child’s/young person’s mental health at the beginning of the study and then 6 and 12 months later. Child and Adolescent Mental Health Services clinical records were reviewed 12 and 18 months after joining the study to look at what care was offered and received through Child and Adolescent Mental Health Services. We also interviewed a range of young people, family members and staff in Child and Adolescent Mental Health Services about their views and experience of using the development and well-being assessment and the summary development and well-being assessment report. At 12-month follow-up, there was no difference in the number receiving an emotional disorder diagnosis; 11% in the development and well-being assessment group and 12% in the control group. The same was found at 18 months (14% vs. 15%). There was no difference between the groups in the time taken to reach a diagnosis or to offer or start treatment, nor was there any significant impact on whether Child and Adolescent Mental Health Services accepted the referral. The interviews showed that young people and families found the development and well-being assessment and report to be useful; however, the development and well-being assessment report was not used consistently, as intended, by clinicians during assessments to aid diagnosis. These findings show that completing the development and well-being assessment after referral into Child and Adolescent Mental Health Services did not have any impact on whether a diagnosis was made by Child and Adolescent Mental Health Services or on the care received.
Kim-Marie A. Dam, Harry B. Gristick, Yancheng E. Li
et al.
Summary: HIV-1 broadly neutralizing antibodies (bNAbs) targeting the CD4-binding site (CD4bs) contain rare features that pose challenges to elicit these bNAbs through vaccination. The IOMA class of CD4bs bNAbs includes fewer rare features and somatic hypermutations (SHMs) to achieve broad neutralization, thus presenting a potentially accessible pathway for vaccine-induced bNAb development. Here, we created a library of IOMA variants in which each SHM was individually reverted to the inferred germline counterpart to investigate the roles of SHMs in conferring IOMA’s neutralization potency and breadth. Impacts on neutralization for each variant were evaluated, and this information was used to design minimally mutated IOMA-class variants (IOMAmin) that incorporated the fewest SHMs required for achieving IOMA’s neutralization breadth. A cryoelectron microscopy (cryo-EM) structure of an IOMAmin variant bound to Env was used to further interpret characteristics of IOMA variants to elucidate how IOMA’s structural features correlate with its neutralization mechanism, informing the design of IOMA-targeting immunogens.
Abstract Background Stroke survivors often experience residual motor dysfunction in their limbs. Additional physical rehabilitation therapies may further improve patients’ functional outcomes. By combining direct interventions targeting the cerebral cortex or subcortical structures with indirect approaches that promote central nervous system reorganization, a closed-loop regulatory system can be established. This integrated approach may generate synergistic effects, thereby enhancing functional recovery outcomes. Methods This 3-week single-center randomized, single-masked study involved participants randomly assigned to either the electroacupuncture (EA) combined with robot-assisted gait training (RAGT) group (n = 22) or the RAGT alone group (n = 23). EA treatment was administered once daily for 30 min, 5 days per week, while RAGT treatment received the same duration of daily sessions. Baseline and endpoint assessments included the Fugl-Meyer lower extremity (FMA-LE) motor function assessment, functional ambulation category (FAC) scale, Berg Balance Scale (BBS) and electroencephalogram. Results After a 3-week intervention period, participants in both groups showed significant improvements in FMA-LE, FAC, and BBS scores compared to baseline levels. The EA combined RAGT group exhibited a reduction in the brain symmetry index within the alpha frequency band, along with enhanced coherence between the CZ electrode and the FCZ, FC2, and C1 electrodes. Furthermore, in the theta frequency band, a shortened average path length and improved global efficiency were observed. Conclusion Both interventions can safely and effectively improve lower limb motor function, and EA combined with RAGT combination therapy may have an advantage in promoting neuroplasticity, which may involve reversing pathological frequency spectrum imbalance after stroke, enhancing functional connections between sensorimotor-related brain regions, and optimizing the topological properties of brain functional networks. Trial registration Chinese Clinical Trial Registry (Registration No.: ChiCTR2500102382)
Abstract Study design Systematic review of Randomised controlled trials. Objectives With the increasing incidence of back pain among children and its untold implications to their future, back education tailored in an effective way would be indicated. However literature appears unsettled. This study aims to review available literature to determine the effect of school-based back education in preventing and managing low back pain in school children. Methods Randomized controlled trials carried out on elementary and secondary school children of ages 6 to 18 years and published in English language were included. Back education taught in hospitals or other settings were excluded. Primary outcome was back pain prevalence and secondary outcomes were constituted from the study characteristics of selected studies which includes: back behavior, knowledge, postural habits, physical activity, fear-avoidance beliefs, back pack carriage, pain intensity, skills and self efficacy. Databases searched were PEDro, HINARI, PubMed, Cochrane, and Google Scholar. Available stiudies from 2000 to March 2022 were retrieved. Quality of studies were assessed using the PEDro scale. Obtained studies were descriptively analyzed. Results A total 8420 studies were retrieved and 8 studies (with 1239 participants) were included in this review. Four studies each assessed back knowledge and back behavior, and two assessed back pain prevalence. There were improvements in back knowledge and back behaviour, but effectiveness of back care education on back pain prevalence was not conclusive. Forms of education used involved the indirect method of conditioning the environment and the direct method which made use of theory, practical lessons and educational books and materials. Conclusion Back care education programmes in schools are effective in improving back care knowledge, behavior and reduction in low back pain frequency. Reduction in back pain prevalence is not conclusive. Back care education could be incorporated as part of schools’ education programmes. Limitations include exclusion of non English language studies and inconsistent outcome measures. Funding source None. Registration This review protocol was registered under the International platform of Registered systematic review and meta-analysis protocol (INPLASY) with the registration number; INPLASY202310044 and DOI number; https://doi.org/10.37766/inplasy2023.1.0044
Patthra Pason, Chakrit Tachaapaikoon, Waralee Suyama
et al.
Colorectal carcinoma (CRC) is one of the most common malignancies, though there are no effective therapeutic regimens at present. This study aimed to investigate the inhibitory effects of mannooligosaccharides extracted from coconut meal (CMOSs) on the proliferation and migration of human colorectal cancer HCT116 cells in vitro. The results showed that CMOSs exhibited significant inhibitory activity against HCT116 cell proliferation in a concentration-dependent manner with less cytotoxic effects on the Vero normal cells. CMOSs displayed the ability to increase the activation of caspase-8, –9, and –3/7, as well as the generation of reactive oxygen species (ROS). Moreover, CMOSs suppressed HCT116 cell migration in vitro. Interestingly, treatment of human microvascular endothelial cells (HMVECs) with CMOSs resulted in the inhibition of cell proliferation, cell migration, and capillary-like tube formation, suggesting its anti-vascular angiogenesis. In summary, the results of this study indicate that CMOSs could be a valuable therapeutic candidate for CRC treatment.
Greta Gasciauskaite, Clara Castellucci, Amos Malorgio
et al.
BackgroundViscoelastic hemostatic assays, such as rotational thromboelastometry (ROTEM) or thromboelastography, enable prompt diagnosis and accelerate targeted treatment. However, the complex interpretation of the results remains challenging. Visual Clot—a situation awareness-based visualization technology—was developed to assist clinicians in interpreting viscoelastic tests.
ObjectiveFollowing a previous high-fidelity simulation study, we analyzed users’ perceptions of the technology, to identify its strengths and limitations from clinicians’ perspectives.
MethodsThis is a mixed qualitative-quantitative study consisting of interviews and a survey. After solving coagulation scenarios using Visual Clot in high-fidelity simulations, we interviewed anesthesia personnel about the perceived advantages and disadvantages of the new tool. We used a template approach to identify dominant themes in interview responses. From these themes, we defined 5 statements, which were then rated on Likert scales in a questionnaire.
ResultsWe interviewed 77 participants and 23 completed the survey. We identified 9 frequently mentioned topics by analyzing the interview responses. The most common themes were “positive design features,” “intuitive and easy to learn,” and “lack of a quantitative component.” In the survey, 21 respondents agreed that Visual Clot is easy to learn and 16 respondents stated that a combination of Visual Clot and ROTEM would help them manage complex hemostatic situations.
ConclusionsA group of anesthesia care providers found Visual Clot well-designed, intuitive, and easy to learn. Participants highlighted its usefulness in emergencies, especially for clinicians inexperienced in coagulation management. However, the lack of quantitative information is an area for improvement.
Fatemeh Tahmasbi, Khadijeh Yazdi, Navisa Sadat Seyedghasemi
et al.
Background: The use of information technology improves the competency of nurses at the bedside. This study was conducted to determine the relationship between informatics competency and clinical competency in nurses working in intensive care units.
Methods: In this cross-sectional study, 135 nurses employed in intensive care units affiliated with Golestan University of Medical Sciences, Iran, were included. The inclusion criteria were having at least a bachelor's degree in nursing, a minimum of six months of work experience in the ICU, and current employment in the ICU. The participants were enrolled in 2023 using a stratified sampling method with proportional allocation. Data were collected using demographic information forms, clinical competency questionnaires, and informatics competency questionnaires. Statistical inferential tests included Mann-Whitney, Kruskal-Wallis, multiple linear regression, and generalized multiple linear regression models. The significance level for all statistical tests was set at 0.05.
Results: The mean scores of the nurses' clinical competency and informatics competency were 58.41±8.80 and 45.67±18.88, respectively. There was no statistically significant correlation between these two variables (r = -0.07, p-value = 0.42). When examining the simultaneous effect of explanatory variables, only work experience in the ICU had a significant association with clinical competency (β = 0.3, P = 0.02). Moreover, informatics competency was significantly associated with gender (β = -12.93, P = 0.001) and the duration of using health information systems (β = -6.22, P = 0.008).
Conclusion: There is no significant relationship between informatics competency and clinical competency among ICU nurses. It is suggested that health system policymakers introduce the components of nurses' informatics competence and emphasize their importance in the clinical setting to improve the quality of care. In addition, nurses should be encouraged to enhance their professional skills and acquire competency in new approaches by gaining updated knowledge.
BACKGROUND:
Owing to the adverse effects of unilateral neglect (UN) on rehabilitation outcomes, fall risk, and activities of daily living, this field has gradually got considerable interest. Notwithstanding, there is presently an absence of efficient portrayals of the entire research field; hence, the motivation behind this study was to dissect and evaluate the literature published in the field of UN following stroke and other nonprogressive brain injuries to identify hotspots and trends for future research.
MATERIALS AND METHODS:
Original articles and reviews related to UN from 1970 to 2022 were retrieved from the Science Citation Index Expanded of the Web of Science Core Collection. CiteSpace, VOSviewer, and Bibliometrix software were used to observe publication fields, countries, and authors.
RESULTS:
A total of 1,202 publications were incorporated, consisting of 92% of original articles, with an overall fluctuating upward trend in the number of publications. Italy, the United Kingdom, and the United States made critical contributions, with Neuropsychologia being the most persuasive academic journal, and Bartolomeo P. ranked first in both the quantity of publications and co-citations. Keywords were divided into four clusters, and burst keyword detection demonstrated that networks and virtual reality might additionally emerge as frontiers of future development and warrant additional attention.
CONCLUSIONS:
UN is an emerging field, and this study presents the first bibliometric analysis to provide a comprehensive overview of research in the field. The insights and guidance garnered from our research on frontiers, trends, and popular topics could prove highly valuable in facilitating the rapid development of this field while informing future research directions.
Medical technology, Diseases of the circulatory (Cardiovascular) system
Image-to-image translation is a common task in computer vision and has been rapidly increasing the impact on the field of medical imaging. Deep learning-based methods that employ conditional generative adversarial networks (cGANs), such as Pix2PixGAN, have been extensively explored to perform image-to-image translation tasks. However, when noisy medical image data are considered, such methods cannot be directly applied to produce clean images. Recently, an augmented GAN architecture named AmbientGAN has been proposed that can be trained on noisy measurement data to synthesize high-quality clean medical images. Inspired by AmbientGAN, in this work, we propose a new cGAN architecture, Ambient-Pix2PixGAN, for performing medical image-to-image translation tasks by use of noisy measurement data. Numerical studies that consider MRI-to-PET translation are conducted. Both traditional image quality metrics and task-based image quality metrics are employed to assess the proposed Ambient-Pix2PixGAN. It is demonstrated that our proposed Ambient-Pix2PixGAN can be successfully trained on noisy measurement data to produce high-quality translated images in target imaging modality.
Nuclear Magnetic Resonance (NMR) and Magnetic Resonance Imaging (MRI) represent versatile tools with diverse applications spanning physics, chemistry, geology, and medical science. This comprehensive review explores the foundational principles of NMR and MRI technologies, elucidating their evolution from fundamental quantum mechanical concepts to widespread applications in medical science. Commencing within a quantum mechanical framework, the concise review emphasizes the significant role played by NMR and MRI in clinical research. Furthermore, it provides a succinct survey of various NMR system types. Conclusively, the review delves into key applications of MRI techniques, presenting valuable methodologies for visualizing internal anatomical structures and soft tissues.
There is a lack of benchmarks for evaluating large language models (LLMs) in long-form medical question answering (QA). Most existing medical QA evaluation benchmarks focus on automatic metrics and multiple-choice questions. While valuable, these benchmarks fail to fully capture or assess the complexities of real-world clinical applications where LLMs are being deployed. Furthermore, existing studies on evaluating long-form answer generation in medical QA are primarily closed-source, lacking access to human medical expert annotations, which makes it difficult to reproduce results and enhance existing baselines. In this work, we introduce a new publicly available benchmark featuring real-world consumer medical questions with long-form answer evaluations annotated by medical doctors. We performed pairwise comparisons of responses from various open and closed-source medical and general-purpose LLMs based on criteria such as correctness, helpfulness, harmfulness, and bias. Additionally, we performed a comprehensive LLM-as-a-judge analysis to study the alignment between human judgments and LLMs. Our preliminary results highlight the strong potential of open LLMs in medical QA compared to leading closed models. Code & Data: https://github.com/lavita-ai/medical-eval-sphere
Image registration is essential for medical image applications where alignment of voxels across multiple images is needed for qualitative or quantitative analysis. With recent advancements in deep neural networks and parallel computing, deep learning-based medical image registration methods become competitive with their flexible modelling and fast inference capabilities. However, compared to traditional optimization-based registration methods, the speed advantage may come at the cost of registration performance at inference time. Besides, deep neural networks ideally demand large training datasets while optimization-based methods are training-free. To improve registration accuracy and data efficiency, we propose a novel image registration method, termed Recurrent Inference Image Registration (RIIR) network. RIIR is formulated as a meta-learning solver to the registration problem in an iterative manner. RIIR addresses the accuracy and data efficiency issues, by learning the update rule of optimization, with implicit regularization combined with explicit gradient input. We evaluated RIIR extensively on brain MRI and quantitative cardiac MRI datasets, in terms of both registration accuracy and training data efficiency. Our experiments showed that RIIR outperformed a range of deep learning-based methods, even with only $5\%$ of the training data, demonstrating high data efficiency. Key findings from our ablation studies highlighted the important added value of the hidden states introduced in the recurrent inference framework for meta-learning. Our proposed RIIR offers a highly data-efficient framework for deep learning-based medical image registration.