Journal of Medical Systems最新文献

Recent advancements in computing have led to the development of artificial intelligence (AI) enabled healthcare technologies. AI-assisted clinical decision support (CDS) integrated into electronic health records (EHR) was demonstrated to have a significant potential to improve clinical care. With the rapid proliferation of AI-assisted CDS, came the realization that a lack of careful consideration of socio-technical issues surrounding the implementation and maintenance of these tools can result in unanticipated consequences, missed opportunities, and suboptimal uptake of these potentially useful technologies. The 48-h Discharge Prediction Tool (48DPT) is a new AI-assisted EHR CDS to facilitate discharge planning. This study aimed to methodologically assess the implementation of 48DPT and identify the barriers and facilitators of adoption and maintenance using the validated implementation science frameworks. The major dimensions of RE-AIM (Reach, Effectiveness, Adoption, Implementation, Maintenance) and the constructs of the Consolidated Framework for Implementation Research (CFIR) frameworks have been used to analyze interviews of 24 key stakeholders using 48DPT. The systematic assessment of the 48DPT implementation allowed us to describe facilitators and barriers to implementation such as lack of awareness, lack of accuracy and trust, limited accessibility, and transparency. Based on our evaluation, the factors that are crucial for the successful implementation of AI-assisted EHR CDS were identified. Future implementation efforts of AI-assisted EHR CDS should engage the key clinical stakeholders in the AI tool development from the very inception of the project, support transparency and explainability of the AI models, provide ongoing education and onboarding of the clinical users, and obtain continuous input from clinical staff on the CDS performance.

In Intensive Care Unit (ICU), the settings of the critical alarms should be sensitive and patient-specific to detect signs of deteriorating health without ringing continuously, but alarm thresholds are not always calibrated to operate this way. An assessment of the connection between critical alarm threshold settings and the patient-specific variables in ICU would deepen our understanding of the issue. The aim of this retrospective descriptive and exploratory study was to assess this relationship using a large cohort of ICU patient stays. A retrospective study was conducted on some 70,000 ICU stays taken from the MIMIC-IV database. Critical alarm threshold values and threshold modification frequencies were examined. The link between these alarm threshold settings and 30 patient variables was then explored by computing the Shapley values of a Random Tree Forest model, fitted with patient variables and alarm settings. The study included 57,667 ICU patient stays. Alarm threshold values and alarm threshold modification frequencies exhibited the same trend: they were influenced by the vital sign monitored, but almost never by the patient’s overall health status. This exploratory study also placed patients’ vital signs as the most important variables, far ahead of medication. In conclusion, alarm settings were rigid and mechanical and were rarely adapted to the evolution of the patient. The management of alarms in ICU appears to be imperfect, and a different approach could result in better patient care and improved quality of life at work for staff.

Hospital digitalization aims to increase efficiency, reduce costs, and/ or improve quality of care. To assess a digitalization-quality relationship, we investigate the association between process digitalization and process and outcome quality. We use data from the German DigitalRadar (DR) project from 2021 and combine these data with two process (preoperative waiting time for osteosynthesis and hip replacement surgery after femur fracture, n = 516 and 574) and two outcome quality indicators (mortality ratio of patients hospitalized for outpatient-acquired pneumonia, n = 1,074; ratio of new decubitus cases, n = 1,519). For each indicator, we run a univariate and a multivariate regression. We measure process digitalization holistically by specifying three models with different explanatory variables: (1) the total DR-score (0 (not digitalized) to 100 (fully digitalized)), (2) the sum of DR-score sub-dimensions’ scores logically associated with an indicator, and (3) sub-dimensions’ separate scores. For the process quality indicators, all but one of the associations are insignificant. A greater DR-score is weakly associated with a lower mortality ratio of pneumonia patients (p < 0.10 in the multivariate regression). In contrast, higher process digitalization is significantly associated with a higher ratio of decubitus cases (p < 0.01 for models (1) and (2), p < 0.05 for two sub-dimensions in model (3)). Regarding decubitus, our finding might be due to better diagnosis, documentation, and reporting of decubitus cases due to digitalization rather than worse quality. Insignificant and inconclusive results might be due to the indicators’ inability to reflect quality variation and digitalization effects between hospitals. For future research, we recommend investigating within hospital effects with longitudinal data.

In the rapidly evolving field of medical image analysis utilizing artificial intelligence (AI), the selection of appropriate computational models is critical for accurate diagnosis and patient care. This literature review provides a comprehensive comparison of vision transformers (ViTs) and convolutional neural networks (CNNs), the two leading techniques in the field of deep learning in medical imaging. We conducted a survey systematically. Particular attention was given to the robustness, computational efficiency, scalability, and accuracy of these models in handling complex medical datasets. The review incorporates findings from 36 studies and indicates a collective trend that transformer-based models, particularly ViTs, exhibit significant potential in diverse medical imaging tasks, showcasing superior performance when contrasted with conventional CNN models. Additionally, it is evident that pre-training is important for transformer applications. We expect this work to help researchers and practitioners select the most appropriate model for specific medical image analysis tasks, accounting for the current state of the art and future trends in the field.

Chat Generative Pretrained Transformer (ChatGPT; OpenAI) is a state-of-the-art large language model that can simulate human-like conversations based on user input. We evaluated the performance of GPT-4 V in the Japanese National Clinical Engineer Licensing Examination using 2,155 questions from 2012 to 2023. The average correct answer rate for all questions was 86.0%. In particular, clinical medicine, basic medicine, medical materials, biological properties, and mechanical engineering achieved a correct response rate of ≥ 90%. Conversely, medical device safety management, electrical and electronic engineering, and extracorporeal circulation obtained low correct answer rates ranging from 64.8% to 76.5%. The correct answer rates for questions that included figures/tables, required numerical calculation, figure/table ∩ calculation, and knowledge of Japanese Industrial Standards were 55.2%, 85.8%, 64.2% and 31.0%, respectively. The reason for the low correct answer rates is that ChatGPT lacked recognition of the images and knowledge of standards and laws. This study concludes that careful attention is required when using ChatGPT because several of its explanations lack the correct description.

Introduction: Chemical mass casualty incidents (MCIs) pose a substantial threat to public health and safety, with the capacity to overwhelm healthcare infrastructure and create societal disorder. Computer simulation systems are becoming an established mechanism to validate these plans due to their versatility, cost-effectiveness and lower susceptibility to ethical problems.

Methods: We created a computer simulation model of an urban subway sarin attack analogous to the 1995 Tokyo sarin incident. We created and combined evacuation, dispersion and victim models with the SIMEDIS computer simulator. We analyzed the effect of several possible approaches such as evacuation policy ('Scoop and Run' vs. 'Stay and Play'), three strategies (on-site decontamination and stabilization, off-site decontamination and stabilization, and on-site stabilization with off-site decontamination), preliminary triage, victim distribution methods, transport supervision skill level, and the effect of search and rescue capacity.

Results: Only evacuation policy, strategy and preliminary triage show significant effects on mortality. The total average mortality ranges from 14.7 deaths in the combination of off-site decontamination and Scoop and Run policy with pretriage, to 24 in the combination of onsite decontamination with the Stay and Play and no pretriage.

Conclusion: Our findings suggest that in a simulated urban chemical MCI, a Stay and Play approach with on-site decontamination will lead to worse outcomes than a Scoop and Run approach with hospital-based decontamination. Quick transport of victims in combination with on-site antidote administration has the potential to save the most lives, due to faster hospital arrival for definitive care.

Artificial intelligence (AI) has become a crucial element of modern technology, especially in the healthcare sector, which is apparent given the continuous development of large language models (LLMs), which are utilized in various domains, including medical beings. However, when it comes to using these LLMs for the medical domain, there's a need for an evaluation platform to determine their suitability and drive future development efforts. Towards that end, this study aims to address this concern by developing a comprehensive Multi-Criteria Decision Making (MCDM) approach that is specifically designed to evaluate medical LLMs. The success of AI, particularly LLMs, in the healthcare domain, depends on their efficacy, safety, and ethical compliance. Therefore, it is essential to have a robust evaluation framework for their integration into medical contexts. This study proposes using the Fuzzy-Weighted Zero-InConsistency (FWZIC) method extended to p, q-quasirung orthopair fuzzy set (p, q-QROFS) for weighing evaluation criteria. This extension enables the handling of uncertainties inherent in medical decision-making processes. The approach accommodates the imprecise and multifaceted nature of real-world medical data and criteria by incorporating fuzzy logic principles. The MultiAtributive Ideal-Real Comparative Analysis (MAIRCA) method is employed for the assessment of medical LLMs utilized in the case study of this research. The results of this research revealed that "Medical Relation Extraction" criteria with its sub-levels had more importance with (0.504) than "Clinical Concept Extraction" with (0.495). For the LLMs evaluated, out of 6 alternatives, ( $A4$ ) "GatorTron S 10B" had the 1st rank as compared to ( $A1$ ) "GatorTron 90B" had the 6th rank. The implications of this study extend beyond academic discourse, directly impacting healthcare practices and patient outcomes. The proposed framework can help healthcare professionals make more informed decisions regarding the adoption and utilization of LLMs in medical settings.

With the proliferation of wound assessment apps across various app stores and the increasing integration of artificial intelligence (AI) in healthcare apps, there is a growing need for a comprehensive evaluation system. Current apps lack sufficient evidence-based reliability, prompting the necessity for a systematic assessment. The objectives of this study are to evaluate the wound assessment and monitoring apps, identify limitations, and outline opportunities for future app development. An electronic search across two major app stores (Google Play store, and Apple App Store) was conducted and the selected apps were rated by three independent raters. A total of 170 apps were discovered, and 10 were selected for review based on a set of inclusion and exclusion criteria. By modifying existing scales, an app rating scale for wound assessment apps is created and used to evaluate the selected ten apps. Our rating scale evaluates apps' functionality and software quality characteristics. Most apps in the app stores, according to our evaluation, do not meet the overall requirements for wound monitoring and assessment. All the apps that we reviewed are focused on practitioners and doctors. According to our evaluation, the app ImitoWound got the highest mean score of 4.24. But this app has 7 criteria among our 11 functionalities criteria. Finally, we have recommended future opportunities to leverage advanced techniques, particularly those involving artificial intelligence, to enhance the functionality and efficacy of wound assessment apps. This research serves as a valuable resource for future developers and researchers seeking to enhance the design of wound assessment-based applications, encompassing improvements in both software quality and functionality.