Decision Support Techniques for determination of the causal relationship between health problems of workers and their work activities.

Reflecting on the complexity and impacts of determination of the causal relationship between health problems of workers and the exercise of their work activities, there is a need to learn about scientific articles that expose techniques to determine this type of causal relationship. There is also a need to reveal whether any article exposes multicriteria decision analysis technique. The aim is to quantify the techniques used to determine the causal relationship between health problems of workers and the exercise of their work activities. Bibliometric analysis was performed, searching for articles in Portuguese, Spanish and English. An advanced search was performed on the website of the ministerial journals portal and then on the Gale Academic OneFile, SciVerse Scopus, Scientific Electronic Library Online (SciELO) and PubMed Central collections. In summary, 38 articles were selected from portal, 50 from Gale Academic OneFile, 20 from SciVerse Scopus, 37 from SciELO and 5 from PubMed Central, totaling 150 articles of interest for analysis of their contents. Among these 150 articles, 33.33% addressed the causal relationship between illness and work, 3.33% described some process related to occupational diagnostic investigation and 0.66%, which represents only one article, exhibited a technique to determine this type of causal relationship: the probability of causality in neoplastic diseases. No article described multicriteria decision analysis method as a technique for determine this type of causal relationship. Therefore, there is a need to carry out and disseminate scientific research on methods to help determine a causal relationship between illness and work.

Ao refletir sobre a complexidade e os impactos do estabelecimento do nexo causal entre o agravo à saúde dos trabalhadores e o exercício de suas atividades laborais, surge a necessidade de conhecer artigos científicos que expõem técnicas para estabelecer esse tipo de nexo. Surge também a necessidade de revelar se algum artigo expõe auxílio multicritério à decisão. O objetivo foi quantificar as técnicas utilizadas no estabelecimento do nexo causal entre o agravo à saúde dos trabalhadores e o exercício de suas atividades laborais. Foi realizada uma análise bibliométrica, buscando artigos em português, espanhol e inglês. Realizou-se uma busca avançada no site do portal ministerial de periódicos e, em seguida, nas coleções Gale Academic OneFile, SciVerse Scopus, Scientific Electronic Library Online (SciELO) e PubMed Central. Em síntese, foram selecionados 38 artigos do portal ministerial de periódicos, 50 da Gale Academic OneFile, 20 da SciVerse Scopus, 37 do SciELO e 5 da PubMed Central, totalizando 150 artigos para análise de conteúdo. Entre esses 150 artigos, 33,33% abordavam o nexo causal entre doença e trabalho, 3,33% descreviam algum processo relacionado à investigação diagnóstica ocupacional, e 0,66%, o que representa apenas um artigo, exibia uma técnica para se estabelecer esse tipo de nexo causal: a probabilidade de causalidade em doenças neoplásicas. Nenhum artigo descrevia o auxílio multicritério à decisão como técnica para estabelecer esse tipo de nexo causal. Portanto, nota-se a necessidade da realização e divulgação de pesquisas científicas sobre métodos de auxílio ao estabelecimento de nexo causal entre doença e trabalho.

Artificial intelligence based real-time prediction of imminent heart failure hospitalisation in patients undergoing non-invasive telemedicine.

Background: Remote patient management may improve prognosis in heart failure. Daily review of transmitted data for early recognition of patients at risk requires substantial resources that represent a major barrier to wide implementation. An automated analysis of incoming data for detection of risk for imminent events would allow focusing on patients requiring prompt medical intervention. Methods: We analysed data of the Telemedical Interventional Management in Heart Failure II (TIM-HF2) randomized trial that were collected during quarterly in-patient visits and daily transmissions from non-invasive monitoring devices. By application of machine learning, we developed and internally validated a risk score for heart failure hospitalisation within seven days following data transmission as estimate of short-term patient risk for adverse heart failure events. Score performance was assessed by the area under the receiver-operating characteristic (ROCAUC) and compared with a conventional algorithm, a heuristic rule set originally applied in the randomized trial. Results: The machine learning model significantly outperformed the conventional algorithm (ROCAUC 0.855 vs. 0.727, p < 0.001). On average, the machine learning risk score increased continuously in the three weeks preceding heart failure hospitalisations, indicating potential for early detection of risk. In a simulated one-year scenario, daily review of only the one third of patients with the highest machine learning risk score would have led to detection of 95% of HF hospitalisations occurring within the following seven days. Conclusions: A machine learning model allowed automated analysis of incoming remote monitoring data and reliable identification of patients at risk of heart failure hospitalisation requiring immediate medical intervention. This approach may significantly reduce the need for manual data review.

An Artificial Intelligence Algorithm for Detection of Severe Aortic Stenosis: A Clinical Cohort Study.

Background: Identifying individuals with severe aortic stenosis (AS) at high risk of mortality remains challenging using current clinical imaging methods. Objectives: The purpose of this study was to evaluate an artificial intelligence decision support algorithm (AI-DSA) to augment the detection of severe AS within a well-resourced health care setting. Methods: Agnostic to clinical information, an AI-DSA trained to identify echocardiographic phenotype associated with an aortic valve area (AVA)<1 cm2 using minimal input data (excluding left ventricular outflow tract measures) was applied to routine transthoracic echocardiograms (TTE) reports from 31,141 U.S. Medicare beneficiaries at an academic medical center (2003-2017). Results: Performance of AI-DSA to detect the phenotype associated with an AVA<1 cm2 was excellent (sensitivity 82.2%, specificity 98.1%, negative predictive value 9.2%, c-statistic = 0.986). In addition to identifying clinical severe AS cases, AI-DSA identified an additional 1,034 (3.3%) individuals with guideline-defined moderate AS but with a similar clinical and TTE phenotype to those with severe AS with low rates of aortic valve replacement (6.6%). Five-year mortality was 75.9% in those with known severe AS, 73.5% in those with a similar phenotype to severe AS, and 44.6% in those without severe AS. The AI-DSA continued to perform well to identify severe AS among those with a depressed left ventricular ejection fraction. Overall rates of aortic valve replacement remained low, even in those with an AVA<1 cm2 (21.9%). Conclusions: Without relying on left ventricular outflow tract measurements, an AI-DSA used echocardiographic reports to reliably identify the phenotype of severe AS. These results suggest possible utility for this AI-DSA to enhance detection of severe AS individuals at risk for adverse outcomes.

Aliado - A design concept of AI for decision support in oncological liver surgery.

BACKGROUND: The interest in artificial intelligence (AI) is increasing. Systematic reviews suggest that there are many machine learning algorithms in surgery, however, only a minority of the studies integrate AI applications in clinical workflows. Our objective was to design and evaluate a concept to use different kinds of AI for decision support in oncological liver surgery along the treatment path. METHODS: In an exploratory co-creation between design experts, surgeons, and data scientists, pain points along the treatment path were identified. Potential designs for AI-assisted solutions were developed and iteratively refined. Finally, an evaluation of the design concept was performed with n = 20 surgeons to get feedback on the different functionalities and evaluate the usability with the System Usability Scale (SUS). Participating surgeons had a mean of 14.0 ± 5.0 years of experience after graduation. RESULTS: The design concept was named "Aliado". Five different scenarios were identified where AI could support surgeons. Mean score of SUS was 68.2 ( ± 13.6 SD). The highest valued functionalities were "individualized prediction of survival, short-term mortality and morbidity", and "individualized recommendation of surgical strategy". CONCLUSION: Aliado is a design prototype that shows how AI could be integrated into the clinical workflow. Even without a fleshed out user interface, the SUS already yielded borderline good results. Expert surgeons rated the functionalities favorably, and most of them expressed their willingness to work with a similar application in the future. Thus, Aliado can serve as a surgical vision of how an ideal AI-based assistance could look like.

Clinicians' roles and necessary levels of understanding in the use of artificial intelligence: A qualitative interview study with German medical students.

BACKGROUND: Artificial intelligence-driven Clinical Decision Support Systems (AI-CDSS) are being increasingly introduced into various domains of health care for diagnostic, prognostic, therapeutic and other purposes. A significant part of the discourse on ethically appropriate conditions relate to the levels of understanding and explicability needed for ensuring responsible clinical decision-making when using AI-CDSS. Empirical evidence on stakeholders' viewpoints on these issues is scarce so far. The present study complements the empirical-ethical body of research by, on the one hand, investigating the requirements for understanding and explicability in depth with regard to the rationale behind them. On the other hand, it surveys medical students at the end of their studies as stakeholders, of whom little data is available so far, but for whom AI-CDSS will be an important part of their medical practice. METHODS: Fifteen semi-structured qualitative interviews (each lasting an average of 56 min) were conducted with German medical students to investigate their perspectives and attitudes on the use of AI-CDSS. The problem-centred interviews draw on two hypothetical case vignettes of AI-CDSS employed in nephrology and surgery. Interviewees' perceptions and convictions of their own clinical role and responsibilities in dealing with AI-CDSS were elicited as well as viewpoints on explicability as well as the necessary level of understanding and competencies needed on the clinicians' side. The qualitative data were analysed according to key principles of qualitative content analysis (Kuckartz). RESULTS: In response to the central question about the necessary understanding of AI-CDSS tools and the emergence of their outputs as well as the reasons for the requirements placed on them, two types of argumentation could be differentiated inductively from the interviewees' statements: the first type, the clinician as a systemic trustee (or "the one relying"), highlights that there needs to be empirical evidence and adequate approval processes that guarantee minimised harm and a clinical benefit from the employment of an AI-CDSS. Based on proof of these requirements, the use of an AI-CDSS would be appropriate, as according to "the one relying", clinicians should choose those measures that statistically cause the least harm. The second type, the clinician as an individual expert (or "the one controlling"), sets higher prerequisites that go beyond ensuring empirical evidence and adequate approval processes. These higher prerequisites relate to the clinician's necessary level of competence and understanding of how a specific AI-CDSS works and how to use it properly in order to evaluate its outputs and to mitigate potential risks for the individual patient. Both types are unified in their high esteem of evidence-based clinical practice and the need to communicate with the patient on the use of medical AI. However, the interviewees' different conceptions of the clinician's role and responsibilities cause them to have different requirements regarding the clinician's understanding and explicability of an AI-CDSS beyond the proof of benefit. CONCLUSIONS: The study results highlight two different types among (future) clinicians regarding their view of the necessary levels of understanding and competence. These findings should inform the debate on appropriate training programmes and professional standards (e.g. clinical practice guidelines) that enable the safe and effective clinical employment of AI-CDSS in various clinical fields. While current approaches search for appropriate minimum requirements of the necessary understanding and competence, the differences between (future) clinicians in terms of their information and understanding needs described here can lead to more differentiated approaches to solutions.

Exploring the potential cost-effectiveness of a new computerised decision support tool for identifying fetal compromise during monitored term labours: an early health economic model.

BACKGROUND: Around 60% of term labours in the UK are continuously monitored using cardiotocography (CTG) to guide clinical labour management. Interpreting the CTG trace is challenging, leading to some babies suffering adverse outcomes and others unnecessary expedited deliveries. A new data driven computerised tool combining multiple clinical risk factors with CTG data (attentive CTG) was developed to help identify term babies at risk of severe compromise during labour. This paper presents an early health economic model exploring its potential cost-effectiveness. METHODS: The model compared attentive CTG and usual care with usual care alone and simulated clinical events, healthcare costs, and infant quality-adjusted life years over 18 years. It was populated using data from a cohort of term pregnancies, the literature, and administrative datasets. Attentive CTG effectiveness was projected through improved monitoring sensitivity/specificity and potential reductions in numbers of severely compromised infants. Scenario analyses explored the impact of including litigation costs. RESULTS: Nationally, attentive CTG could potentially avoid 10,000 unnecessary alerts in labour and 2400 emergency C-section deliveries through improved specificity. A reduction of 21 intrapartum stillbirths amongst severely compromised infants was also predicted with improved sensitivity. Attentive CTG could potentially lead to cost savings and health gains with a probability of being cost-effective at £25,000 per QALY ranging from 70 to 95%. Potential exists for further cost savings if litigation costs are included. CONCLUSIONS: Attentive CTG could offer a cost-effective use of healthcare resources. Prospective patient-level studies are needed to formally evaluate its effectiveness and economic impact in routine clinical practice.

Integrating tabular data through image conversion for enhanced diagnosis: A novel intelligent decision support system for stratifying obstructive sleep apnoea patients using convolutional neural networks.

Objective: High-dimensional databases make it difficult to apply traditional learning algorithms to biomedical applications. Recent developments in computer technology have introduced deep learning (DL) as a potential solution to these difficulties. This study presents a novel intelligent decision support system based on a novel interpretation of data formalisation from tabular data in DL techniques. Once defined, it is used to diagnose the severity of obstructive sleep apnoea, distinguishing between moderate to severe and mild/no cases. Methods: The study uses a complete database extract from electronic health records of 2472 patients, including anthropometric data, habits, medications, comorbidities, and patient-reported symptoms. The novelty of this methodology lies in the initial processing of the patients' data, which is formalised into images. These images are then used as input to train a convolutional neural network (CNN), which acts as the inference engine of the system. Results: The initial tests of the system were performed on a set of 247 samples from the Pulmonary Department of the Álvaro Cunqueiro Hospital in Vigo (Galicia, Spain), with an AUC value of ≈ 0.8. Conclusions: This study demonstrates the benefits of an intelligent decision support system based on a novel data formalisation approach that allows the use of advanced DL techniques starting from tabular data. In this way, the ability of CNNs to recognise complex patterns using visual elements such as gradients and contrasts can be exploited. This approach effectively addresses the challenges of analysing large amounts of tabular data and reduces common problems such as bias and variance, resulting in improved diagnostic accuracy.

eConsent administered by Community Health Workers in a study using the Trials within Cohorts (TwiCs) design-Experiences from the Community-Based chronic Care Lesotho (ComBaCaL) project.

Improving access to essential health services requires the development of innovative health service delivery models and their scientific assessment in often large-scale pragmatic trials. In many low- and middle-income countries, lay Community Health Workers (CHWs) play an important role in delivering essential health services. As trusted members of their communities with basic medical training, they may also contribute to health data collection. Digital clinical decision support applications may facilitate the involvement of CHWs in service delivery and data collection. Electronic consent (eConsent) can streamline the consent process that is required if the collected data is used for the scientific purposes. Here, we describe the experiences of using eConsent in the Community-Based chronic Care Lesotho (ComBaCaL) cohort study and multiple nested pragmatic cluster-randomized trials assessing CHW-led care delivery models for type 2 diabetes and arterial hypertension using the Trials within Cohorts (TwiCs) design. More than a hundred CHWs, acting both as service providers and data collectors in remote villages of Lesotho utilize an eConsent application that is linked to a tailored clinical decision support and data collection application. The eConsent application presents simplified consent information and generates personalized consent forms that are signed electronically on a tablet and then uploaded to the database of the clinical decision support application. This significantly streamlines the consent process and allows for quality consent documentation through timely central monitoring, facilitating the CHW-led management of a large-scale population-based cohort in a remote low-resource area with continuous enrollment-currently at more than 16,000 participants.

Development and validation of a sepsis risk index supporting early identification of ICU-acquired sepsis: An observational study.

BACKGROUND: Sepsis is a threat to global health, and domestically is the major cause of in-hospital mortality. Due to increases in inpatient morbidity and mortality resulting from sepsis, healthcare providers (HCPs) would accrue significant benefits from identifying the syndrome early and treating it promptly and effectively. Prompt and effective detection, diagnosis, and treatment of sepsis requires frequent monitoring and assessment of patient vital signs and other relevant data present in the electronic health record. METHODS: This study explored the development of machine learning-based models to generate a novel sepsis risk index (SRI) which is an intuitive 0-100 marker that reflects the risk of a patient acquiring sepsis or septic shock and assists in timely diagnosis. Machine learning models were developed and validated using openly accessible critical care databases. The model was developed using a single database (from one institution) and validated on a separate database consisting of patient data collected across multiple ICUs. RESULTS: The developed model achieved an area under the receiver operating characteristic curve of 0.82 and 0.84 for the diagnosis of sepsis and septic shock, respectively, with a sensitivity and specificity of 79.1% [75.1, 82.7] and 73.3% [72.8, 73.8] for a sepsis diagnosis and 83.8% [80.8, 86.5] and 73.3% [72.8, 73.8] for a septic shock diagnosis. CONCLUSION: The SRI provides critical care HCPs with an intuitive quantitative measure related to the risk of a patient having or acquiring a life-threatening infection. Evaluation of the SRI over time may provide HCPs the ability to initiate protective interventions (e.g. targeted antibiotic therapy).

Construction and Validation of an Assistant Decision-Making Model for Platelet Transfusion Refractoriness in Patients with Acute Myeloid Leukemia.

Background: Platelet transfusion refractoriness (PTR) is a complication of multiple transfusions in patients with hematological malignancies. PTR may induce a series of adverse events, such as delaying the treatment of the primary disease and life-threatening bleeding. Early prediction of PTR holds promise in facilitating prompt adjustments to treatment strategies by clinicians. Methods: We collected the clinical data of 250 patients with acute myeloid leukemia (AML). Subsequently, the patients were randomly divided into a training cohort and a validation cohort at a ratio of 7:3. The least absolute shrinkage and selection operator (LASSO) and multivariate logistic-regression methods were used to select characteristic variables. Assessment of the model was conducted through the receiver operating characteristic (ROC), calibration curve and decision curve analysis (DCA). Results: Out of 250 patients with AML, 95 individuals (38.0%) experienced PTR. Among those with positive platelet associated antibodies (PAAs), the incidence of PTR was 66.7% (30/45), while among patients positive for human leukocyte antigen(HLA)-I antibodies, the PTR incidence was 56.5% (48/85). The final predictive model incorporated risk factors such as KIT mutations, splenomegaly, the number of HLA-I antibodies, and positive PAAs. A prediction nomogram model was constructed based on these four risk factors. The LASSO-logistic regression model demonstrated excellent discrimination, calibration, and clinical decision value. Conclusion: The LASSO-logistic regression model in the study can better predict the risk of PTR. The study includes both PAAs and HLA antibodies, expanding the field of work that has not been involved in the previous prediction model of PTR.

Comparative Study to Evaluate the Accuracy of Differential Diagnosis Lists Generated by Gemini Advanced, Gemini, and Bard for a Case Report Series Analysis: Cross-Sectional Study.

BACKGROUND: Generative artificial intelligence (GAI) systems by Google have recently been updated from Bard to Gemini and Gemini Advanced as of December 2023. Gemini is a basic, free-to-use model after a user's login, while Gemini Advanced operates on a more advanced model requiring a fee-based subscription. These systems have the potential to enhance medical diagnostics. However, the impact of these updates on comprehensive diagnostic accuracy remains unknown. OBJECTIVE: This study aimed to compare the accuracy of the differential diagnosis lists generated by Gemini Advanced, Gemini, and Bard across comprehensive medical fields using case report series. METHODS: We identified a case report series with relevant final diagnoses published in the American Journal Case Reports from January 2022 to March 2023. After excluding nondiagnostic cases and patients aged 10 years and younger, we included the remaining case reports. After refining the case parts as case descriptions, we input the same case descriptions into Gemini Advanced, Gemini, and Bard to generate the top 10 differential diagnosis lists. In total, 2 expert physicians independently evaluated whether the final diagnosis was included in the lists and its ranking. Any discrepancies were resolved by another expert physician. Bonferroni correction was applied to adjust the P values for the number of comparisons among 3 GAI systems, setting the corrected significance level at P value <.02. RESULTS: In total, 392 case reports were included. The inclusion rates of the final diagnosis within the top 10 differential diagnosis lists were 73% (286/392) for Gemini Advanced, 76.5% (300/392) for Gemini, and 68.6% (269/392) for Bard. The top diagnoses matched the final diagnoses in 31.6% (124/392) for Gemini Advanced, 42.6% (167/392) for Gemini, and 31.4% (123/392) for Bard. Gemini demonstrated higher diagnostic accuracy than Bard both within the top 10 differential diagnosis lists (P=.02) and as the top diagnosis (P=.001). In addition, Gemini Advanced achieved significantly lower accuracy than Gemini in identifying the most probable diagnosis (P=.002). CONCLUSIONS: The results of this study suggest that Gemini outperformed Bard in diagnostic accuracy following the model update. However, Gemini Advanced requires further refinement to optimize its performance for future artificial intelligence-enhanced diagnostics. These findings should be interpreted cautiously and considered primarily for research purposes, as these GAI systems have not been adjusted for medical diagnostics nor approved for clinical use.

The ethical requirement of explainability for AI-DSS in healthcare: a systematic review of reasons.

BACKGROUND: Despite continuous performance improvements, especially in clinical contexts, a major challenge of Artificial Intelligence based Decision Support Systems (AI-DSS) remains their degree of epistemic opacity. The conditions of and the solutions for the justified use of the occasionally unexplainable technology in healthcare are an active field of research. In March 2024, the European Union agreed upon the Artificial Intelligence Act (AIA), requiring medical AI-DSS to be ad-hoc explainable or to use post-hoc explainability methods. The ethical debate does not seem to settle on this requirement yet. This systematic review aims to outline and categorize the positions and arguments in the ethical debate. METHODS: We conducted a literature search on PubMed, BASE, and Scopus for English-speaking scientific peer-reviewed publications from 2016 to 2024. The inclusion criterion was to give explicit requirements of explainability for AI-DSS in healthcare and reason for it. Non-domain-specific documents, as well as surveys, reviews, and meta-analyses were excluded. The ethical requirements for explainability outlined in the documents were qualitatively analyzed with respect to arguments for the requirement of explainability and the required level of explainability. RESULTS: The literature search resulted in 1662 documents; 44 documents were included in the review after eligibility screening of the remaining full texts. Our analysis showed that 17 records argue in favor of the requirement of explainable AI methods (xAI) or ad-hoc explainable models, providing 9 categories of arguments. The other 27 records argued against a general requirement, providing 11 categories of arguments. Also, we found that 14 works advocate the need for context-dependent levels of explainability, as opposed to 30 documents, arguing for context-independent, absolute standards. CONCLUSIONS: The systematic review of reasons shows no clear agreement on the requirement of post-hoc explainability methods or ad-hoc explainable models for AI-DSS in healthcare. The arguments found in the debate were referenced and responded to from different perspectives, demonstrating an interactive discourse. Policymakers and researchers should watch the development of the debate closely. Conversely, ethicists should be well informed by empirical and technical research, given the frequency of advancements in the field.

Towards safer tower crane operations: An innovative knowledge-based decision support system for automated safety risk assessment.

INTRODUCTION: Tower cranes are commonly employed in construction projects, despite presenting significant hazards to the workforce involved. METHOD: To address these safety concerns, a Knowledge-Based Decision-Support System for Safety Risk Assessment (KBDSS-SRA) has been developed. The system's capacity to thoroughly evaluate associated risks is illustrated through its utilization in various construction endeavors. RESULTS: The system accomplishes the following goals: (1) compiles essential risk factors specific to tower crane operations, (2) identifies critical safety risks that jeopardize worker well-being, (3) examines and assesses the identified safety risks, and (4) automates the labor-intensive and error-prone processes of safety risk assessment. The KBDSS-SRA assists safety management personnel in formulating well-grounded decisions and implementing effective measures to enhance the safety of tower crane operations. PRACTICAL APPLICATIONS: This is facilitated by an advanced computerized tool that underscores the paramount significance of safety risks and suggests strategies for their future mitigation.

Pediatric septic shock estimation using deep learning and electronic medical records.

BACKGROUND: Diagnosing pediatric septic shock is difficult due to the complex and often impractical traditional criteria, such as systemic inflammatory response syndrome (SIRS), which result in delays and higher risks. This study aims to develop a deep learning-based model using SIRS data for early diagnosis in pediatric septic shock cases. METHODS: The study analyzed data from pediatric patients (<18 years old) admitted to a tertiary hospital from January 2010 to July 2023. Vital signs, lab tests, and clinical information were collected. Septic shock cases were identified using SIRS criteria and inotrope use. A deep learning model was trained and evaluated using the area under the receiver operating characteristics curve (AUROC) and area under the precision-recall curve (AUPRC). Variable contributions were analyzed using the Shapley additive explanation value. RESULTS: The analysis, involving 9,616,115 measurements, identified 34,696 septic shock cases (0.4%). Oxygen supply was crucial for 41.5% of the control group and 20.8% of the septic shock group. The final model showed strong performance, with an AUROC of 0.927 and AUPRC of 0.879. Key influencers were age, oxygen supply, sex, and partial pressure of carbon dioxide, while body temperature had minimal impact on estimation. CONCLUSIONS: The proposed deep learning model simplifies early septic shock diagnosis in pediatric patients, reducing the diagnostic workload. Its high accuracy allows timely treatment, but external validation through prospective studies is needed.

Large Language Model Prompting Techniques for Advancement in Clinical Medicine.

Large Language Models (LLMs have the potential to revolutionize clinical medicine by enhancing healthcare access, diagnosis, surgical planning, and education. However, their utilization requires careful, prompt engineering to mitigate challenges like hallucinations and biases. Proper utilization of LLMs involves understanding foundational concepts such as tokenization, embeddings, and attention mechanisms, alongside strategic prompting techniques to ensure accurate outputs. For innovative healthcare solutions, it is essential to maintain ongoing collaboration between AI technology and medical professionals. Ethical considerations, including data security and bias mitigation, are critical to their application. By leveraging LLMs as supplementary resources in research and education, we can enhance learning and support knowledge-based inquiries, ultimately advancing the quality and accessibility of medical care. Continued research and development are necessary to fully realize the potential of LLMs in transforming healthcare.

Percentage area reduction at week 4 as a prognostic indicator of complete healing in patients treated with standard of care: a post hoc analysis.

Early indicators of healing provide valuable information on the potential benefit of treatment. In patients with hard-to-heal (chronic) diabetic foot ulcers (DFUs), timely intervention is critical. Ulcers that fail to show measurable progress within four weeks of treatment are considered recalcitrant. These ulcers increase the risk of soft tissue infection, osteomyelitis and lower extremity amputation. A prognostic indicator or surrogate marker allows for rapid evaluation of treatment efficacy and safety. An inverse correlation between a percentage area reduction (PAR) of ≤50% at week 4 and complete healing by week 12 has been previously established; however, the data were derived from a standard of care (SoC) arm of clinical trials that are over a decade old. In this post hoc analysis, data from a large multicentre prospective randomised controlled trial were reviewed to assess PAR at week 4 as a prognostic indicator in patients treated with SoC. Overall, 65.4% (17/26) of patients with PAR >50% at week 4 achieved complete closure at week 12. The receiver operating characteristic (ROC) curve for area reduction by week 4 showed strong discrimination for predicting non-healing (area under the ROC curve: 0.92; p<0.001; positive predictive value: 70.6%; negative predictive value: 87.2%). These findings are consistent with previous studies and support the use of four-week PAR as a prognostic indicator.

An automated dispensing cabinet alert influences anesthesia provider medication preparation in a remifentanil waste reduction initiative.

STUDY OBJECTIVE: To decrease the occurrence of remifentanil waste of 1 mg or more (1 full vial) by 25 % in our surgical division while maintaining satisfaction of 60 % of providers by using a remifentanil mixing workflow. DESIGN: A time series-design quality improvement initiative targeted preventable remifentanil waste. A period of active interventions, followed by a pause and reinstatement of a system intervention, was used to validate its effectiveness. SETTING: An academic medical center in the US with 1219 inpatient beds, performing 144,418 surgical cases in 2019 and 127,341 surgical cases in 2020, in 148 operating rooms. INTERVENTIONS: Individual- and system-level interventions provided education on the issues of preventable waste, access to a remifentanil dose calculator, and an automated dispensing cabinet (ADC) alert to halt wasteful practice. MEASUREMENTS: Preventable remifentanil waste was identified as disposing of intravenous infusion bags containing 1 mg or more or 1 full vial or more of unused medication. Data were retrieved from ADC reports. A preimplementation and postimplementation survey of anesthesia providers assessed workflow attitudes, perceptions, and satisfaction surrounding remifentanil mixing. MAIN RESULTS: Preventable remifentanil waste (≥1 mg or ≥ 1 full vial) decreased significantly from 22.0 % of cases using remifentanil at baseline to 16.7 % of cases using remifentanil (odds ratio, 0.71; 95 % CI, 0.60-0.84; P < .001) during the final data collection. Individual-level interventions of education, remifentanil dose calculator, and practice champions did not significantly affect waste while unpaired from the system intervention of the ADC alert. CONCLUSIONS: The implementation of an ADC alert reduced preventable remifentanil waste among anesthesia providers.

Integrating federated learning for improved counterfactual explanations in clinical decision support systems for sepsis therapy.

In recent years, we have witnessed both artificial intelligence obtaining remarkable results in clinical decision support systems (CDSSs) and explainable artificial intelligence (XAI) improving the interpretability of these models. In turn, this fosters the adoption by medical personnel and improves trustworthiness of CDSSs. Among others, counterfactual explanations prove to be one such XAI technique particularly suitable for the healthcare domain due to its ease of interpretation, even for less technically proficient staff. However, the generation of high-quality counterfactuals relies on generative models for guidance. Unfortunately, training such models requires a huge amount of data that is beyond the means of ordinary hospitals. In this paper, we therefore propose to use federated learning to allow multiple hospitals to jointly train such generative models while maintaining full data privacy. We demonstrate the superiority of our approach compared to locally generated counterfactuals. Moreover, we prove that generative models for counterfactual generation that are trained using federated learning in a suitable environment perform only marginally worse compared to centrally trained ones while offering the benefit of data privacy preservation. Finally, we integrate our method into a prototypical CDSS for treatment recommendation for sepsis patients, thus providing a proof of concept for real-world application as well as insights and sanity checks from clinical application.

Seeing Bradycardia: How Ultrasound Improves Medical Decision-Making.

There is a broad differential for new-onset cardiac dysrhythmia, and the rapid identification of the underlying cause of these cardiac emergencies can be lifesaving. Identifying wall motion abnormalities on point-of-care ultrasound (POCUS) is not a core echocardiography application for Emergency Medicine (EM) physicians. However, ruling in a regional wall motion abnormality can expedite patient-centered care and assist the busy EM physician in high-risk cases.