Design and optimization of dynamic reliability-driven order allocation and inventory management decision model.

Efficient order allocation and inventory management are essential for the success of supply chain operations in today's dynamic and competitive business environment. This research introduces an innovative decision-making model incorporating dependability factors into redesigning and optimizing order allocation and inventory management systems. The proposed model aims to enhance the overall reliability of supply chain operations by integrating stochastic factors such as demand fluctuations, lead time uncertainty, and variable supplier performance. The system, named Dynamic Reliability-Driven Order Allocation and Inventory Management (DROAIM), combines stochastic models, reliability-based supplier evaluation, dynamic algorithms, and real-time analytics to create a robust and flexible framework for supply chain operations. It evaluates the dependability of suppliers, transportation networks, and internal procedures, offering a comprehensive approach to managing supply chain operations. A case study and simulations were conducted to assess the efficacy of the proposed approach. The findings demonstrate significant improvements in the overall reliability of supply chain operations, reduced stockout occurrences, and optimized inventory levels. Additionally, the model shows adaptability to various industry-specific challenges, making it a versatile tool for practitioners aiming to enhance their supply chain resilience. Ultimately, this research contributes to existing knowledge by providing a thorough decision-making framework incorporating dependability factors into order allocation and inventory management processes. Practitioners and experts can implement this framework to address uncertainties in their operations.

A variant-informed decision support system for tackling COVID-19: a transfer learning and multi-attribute decision-making approach.

The global impact of the COVID-19 pandemic, characterized by its extensive societal, economic, and environmental challenges, escalated with the emergence of variants of concern (VOCs) in 2020. Governments, grappling with the unpredictable evolution of VOCs, faced the need for agile decision support systems to safeguard nations effectively. This article introduces the Variant-Informed Decision Support System (VIDSS), designed to dynamically adapt to each variant of concern's unique characteristics. Utilizing multi-attribute decision-making (MADM) techniques, VIDSS assesses a country's performance by considering improvements relative to its past state and comparing it with others. The study incorporates transfer learning, leveraging insights from forecast models of previous VOCs to enhance predictions for future variants. This proactive approach harnesses historical data, contributing to more accurate forecasting amid evolving COVID-19 challenges. Results reveal that the VIDSS framework, through rigorous K-fold cross-validation, achieves robust predictive accuracy, with neural network models significantly benefiting from transfer learning. The proposed hybrid MADM approach integrated approaches yield insightful scores for each country, highlighting positive and negative criteria influencing COVID-19 spread. Additionally, feature importance, illustrated through SHAP plots, varies across variants, underscoring the evolving nature of the pandemic. Notably, vaccination rates, intensive care unit (ICU) patient numbers, and weekly hospital admissions consistently emerge as critical features, guiding effective pandemic responses. These findings demonstrate that leveraging past VOC data significantly improves future variant predictions, offering valuable insights for policymakers to optimize strategies and allocate resources effectively. VIDSS thus stands as a pivotal tool in navigating the complexities of COVID-19, providing dynamic, data-driven decision support in a continually evolving landscape.

Development of a Cohort Analytics Tool for Monitoring Progression Patterns in Cardiovascular Diseases: Advanced Stochastic Modeling Approach.

BACKGROUND: The World Health Organization (WHO) reported that cardiovascular diseases (CVDs) are the leading cause of death worldwide. CVDs are chronic, with complex progression patterns involving episodes of comorbidities and multimorbidities. When dealing with chronic diseases, physicians often adopt a "watchful waiting" strategy, and actions are postponed until information is available. Population-level transition probabilities and progression patterns can be revealed by applying time-variant stochastic modeling methods to longitudinal patient data from cohort studies. Inputs from CVD practitioners indicate that tools to generate and visualize cohort transition patterns have many impactful clinical applications. The resultant computational model can be embedded in digital decision support tools for clinicians. However, to date, no study has attempted to accomplish this for CVDs. OBJECTIVE: This study aims to apply advanced stochastic modeling methods to uncover the transition probabilities and progression patterns from longitudinal episodic data of patient cohorts with CVD and thereafter use the computational model to build a digital clinical cohort analytics artifact demonstrating the actionability of such models. METHODS: Our data were sourced from 9 epidemiological cohort studies by the National Heart Lung and Blood Institute and comprised chronological records of 1274 patients associated with 4839 CVD episodes across 16 years. We then used the continuous-time Markov chain method to develop our model, which offers a robust approach to time-variant transitions between disease states in chronic diseases. RESULTS: Our study presents time-variant transition probabilities of CVD state changes, revealing patterns of CVD progression against time. We found that the transition from myocardial infarction (MI) to stroke has the fastest transition rate (mean transition time 3, SD 0 days, because only 1 patient had a MI-to-stroke transition in the dataset), and the transition from MI to angina is the slowest (mean transition time 1457, SD 1449 days). Congestive heart failure is the most probable first episode (371/840, 44.2%), followed by stroke (216/840, 25.7%). The resultant artifact is actionable as it can act as an eHealth cohort analytics tool, helping physicians gain insights into treatment and intervention strategies. Through expert panel interviews and surveys, we found 9 application use cases of our model. CONCLUSIONS: Past research does not provide actionable cohort-level decision support tools based on a comprehensive, 10-state, continuous-time Markov chain model to unveil complex CVD progression patterns from real-world patient data and support clinical decision-making. This paper aims to address this crucial limitation. Our stochastic model-embedded artifact can help clinicians in efficient disease monitoring and intervention decisions, guided by objective data-driven insights from real patient data. Furthermore, the proposed model can unveil progression patterns of any chronic disease of interest by inputting only 3 data elements: a synthetic patient identifier, episode name, and episode time in days from a baseline date.

An Institutional Febrile Neutropenia Protocol Improved the Antibacterial Treatment and Encouraged the Development of a Computerized Clinical Decision Support System.

We investigated the influence of a local guideline on the quality of febrile neutropenia (FN) management and the applicability of a computerized decision support system (CDSS) using real-life data. The study included 227 FN patients between April 2016 and January 2019. The primary outcome measure was the achievement of a 20% increase in the rate of appropriate empirical treatment of FN in bacteremic patients. The compatibility of the CDSS (the development of which was completed in November 2021) with local protocols was tested using standard patient scenarios and empirical antibiotic recommendations for bacteremic FN patients. In total, 91 patients were evaluated before (P1: between April 2016 and May 2017) and 136 after (P2: between May 2017 and January 2019) the guideline's release (May 2017). The demographic characteristics were similar. Appropriate empirical antibacterial treatment was achieved in 58.3% of P1 and 88.1% of P2 patients (p = 0.006). The need for escalation of antibacterial treatment was significantly lower in P2 (49.5% vs. 35.3%; p = 0.03). In P2, the performance of the CDSS and consulting physicians was similar (CDSS 88.8% vs. physician 88.83%; p = 1) regarding appropriate empirical antibacterial treatment. The introduction of the local guideline improved the appropriateness of initial empirical treatment and reduced escalation rates in FN patients. The high rate of compliance of the CDSS with the local guideline-based decisions in P2 highlights the usefulness of the CDSS for these patients.

GastricAITool: A Clinical Decision Support Tool for the Diagnosis and Prognosis of Gastric Cancer.

BACKGROUND/OBJECTIVE: Gastric cancer (GC) is a complex disease representing a significant global health concern. Advanced tools for the early diagnosis and prediction of adverse outcomes are crucial. In this context, artificial intelligence (AI) plays a fundamental role. The aim of this work was to develop a diagnostic and prognostic tool for GC, providing support to clinicians in critical decision-making and enabling personalised strategies. METHODS: Different machine learning and deep learning techniques were explored to build diagnostic and prognostic models, ensuring model interpretability and transparency through explainable AI methods. These models were developed and cross-validated using data from 590 Spanish Caucasian patients with primary GC and 633 cancer-free individuals. Up to 261 variables were analysed, including demographic, environmental, clinical, tumoral, and genetic data. Variables such as Helicobacter pylori infection, tobacco use, family history of GC, TNM staging, metastasis, tumour location, treatment received, gender, age, and genetic factors (single nucleotide polymorphisms) were selected as inputs due to their association with the risk and progression of the disease. RESULTS: The XGBoost algorithm (version 1.7.4) achieved the best performance for diagnosis, with an AUC value of 0.68 using 5-fold cross-validation. As for prognosis, the Random Survival Forest algorithm achieved a C-index of 0.77. Of interest, the incorporation of genetic data into the clinical-demographics models significantly increased discriminatory ability in both diagnostic and prognostic models. CONCLUSIONS: This article presents GastricAITool, a simple and intuitive decision support tool for the diagnosis and prognosis of GC.

In Silico Decoding of Parkinson's: Speech & Writing Analysis.

Background: Parkinson's disease (PD) has transitioned from a rare condition in 1817 to the fastest-growing neurological disorder globally. The significant increase in cases from 2.5 million in 1990 to 6.1 million in 2016, coupled with predictions of a further doubling by 2040, underscores an impending healthcare challenge. This escalation aligns with global demographic shifts, including rising life expectancy and a growing global population. The economic impact, notably in the U.S., reached $51.9 billion in 2017, with projections suggesting a 46% increase by 2037, emphasizing the substantial socio-economic implications for both patients and caregivers. Coupled with a worldwide demand for health workers that is expected to rise to 80 million by 2030, we have fertile ground for a pandemic. Methods: Our transdisciplinary research focused on early PD detection through running speech and continuous handwriting analysis, incorporating medical, biomedical engineering, AI, and linguistic expertise. The cohort comprised 30 participants, including 20 PD patients at stages 1-4 on the Hoehn and Yahr scale and 10 healthy controls. We employed advanced AI techniques to analyze correlation plots generated from speech and handwriting features, aiming to identify prodromal PD biomarkers. Results: The study revealed distinct speech and handwriting patterns in PD patients compared to controls. Our ParkinsonNet model demonstrated high predictive accuracy, with F1 scores of 95.74% for speech and 96.72% for handwriting analyses. These findings highlight the potential of speech and handwriting as effective early biomarkers for PD. Conclusions: The integration of AI as a decision support system in analyzing speech and handwriting presents a promising approach for early PD detection. This methodology not only offers a novel diagnostic tool but also contributes to the broader understanding of PD's early manifestations. Further research is required to validate these findings in larger, diverse cohorts and to integrate these tools into clinical practice for timely PD pre-diagnosis and management.

Open-sourced modeling and simulating tools for decision-makers during an emerging pandemic or epidemic - Systematic evaluation of utility and usability: A scoping review update.

Introduction: The COVID-19 pandemic had devastating effects on health systems globally. Emerging infectious diseases and pandemics will persist as a global health threat and preparedness for an evidence based response becomes challenging for decision makers. Epidemiological modeling can and has supported decision-making throughout pandemics. This study provides an update of the review "Publicly available software tools for decision-makers during an emergent epidemic-Systematic evaluation of utility and usability"1. Research question: What epidemiological modeling tools for decision-makers are open-sourced available for the usage in emerging epidemics or pandemics and how useful and user-friendly are these tools? Methods: A scoping review was conducted. We identified relevant studies through a search of peer-reviewed (Medline Ovid, Embase Ovid, PubMed, Cochrane) and gray literature databases, search engines such as Google, searches through stakeholder websites as well as expert consultations. Results: Of the 66 identified epidemiological modeling tools, 29 were included and qualitatively assessed using five-point-rating scales. The tools showed a good baseline of user-friendliness with variations in assessed components, features and utility. Room for improvement was found, specifically the capability to incorporate external data sources, detailed population descriptions, and geographic resolution. Discussion: Development efforts should prioritize clear communication of uncertainties and expert review processes. Trainings for specific tools should be considered. Conclusion: Tool usage can enhance decision-making when adapted to the user's needs and purpose. They should be consulted critically rather than followed blindly.

Adjusting the timing of inseminations to the time lag on luteolysis alerts results in higher conception in dairy cattle.

Dairy cow fertility is a complex trait that depends on the cow's physiological status, the farm's environmental and management conditions, and their interactions. Already the slightest improvement in fertility can positively impact a farm's profitability and sustainability. In research, milk progesterone (P4) has often been used as an accurate and feasible way to identify a dairy cow's reproduction status. Moreover, in Europe and Canada, it has been used to improve fertility management on commercial farms as it allows to accurately identify reproduction issues, pregnancy and the optimal insemination window. An on-farm P4 device (OPD) automatically samples, measures and monitors the milk P4 concentration of individual cows. To this end, the P4 data is smoothed to be robust for measurement errors and outliers, and fixed thresholds are used to estimate the time of luteolysis preceding ovulation, thereby generating a luteolysis alert (LA). By smoothing the P4 data, the OPD introduces a time lag on the LA. Variation in this time lag is not considered in the estimation of the optimal insemination window that is advised to the farmer. Ignoring this variation might decrease the accuracy of the optimal insemination window and, therefore, decreases the likelihood of conception. We hypothesize that considering the length of the time lag and adapting the advice accordingly improves the conception rate. This observational retrospective study uses an extensive data set from 17 commercial dairy farms that are equipped with an OPD. We estimated the time lag on the alerts and evaluated their relationship with the interval from LA to insemination for successful (n = 3721) and unsuccessful inseminations (n = 3896) separately. Results showed that the probability of conception increases when a longer LA time lag is compensated with a shorter interval from LA to insemination and vice versa. In addition, for successful inseminations, we found a clear negative relation between the time lag and the interval from LA to insemination and the interval was significantly shorter when the time lag of the LA was longer. This negative relation between time lag and interval from LA to insemination was less pronounced for unsuccessful inseminations. Additionally, we evaluated the conception rates for inseminations that are performed too early, in time or too late with respect to the optimal insemination window advised by the OPD, in function of their associated time lags. We found that, for inseminations that were preceded by a short time lag (<8 h), the conception rate was 17.5 percentage points higher when cows were inseminated later than advised. Likewise, when inseminations were preceded by a long time lag (≥24 h), we found that the conception rate was 13 percentage points higher when cows were inseminated earlier than advised. Our results suggest that farmers using an OPD could potentially increase their conception success by compensating the variable time lag on the LA by adapting the interval from alert to insemination accordingly. This could be used to develop reproductive management strategies to improve reproductive performance on those farms, which can positively impact their sustainability.

Prescription drug monitoring program in Australia: a qualitative study of stakeholders' experiences and perceptions of a state-wide implementation.

BACKGROUND: Prescription Drug Monitoring Programs (PDMPs) are increasingly implemented across the globe with aims of managing and mitigating risks relating to high-risk prescription medicines. There is limited research focused on identifying strategies or processes for large-scale PDMP implementation. This study aimed to identify strategies perceived as necessary for successful state-wide implementation of a PDMP by exploring the experiences and perceptions of stakeholders responsible for the implementation in New South Wales (NSW), Australia: to identify (1) the drivers of implementation; (2) perceived strategies that worked well; (3) barriers to implementation; and (4) the elements needed for long-term success of SafeScript NSW. METHODS: This study used a qualitative descriptive design. Theoretical frameworks used to design interview questions and guide thematic analysis were the non-adoption, abandonment, scale-up, spread, and sustainability (NASSS) framework and Quadruple Aim framework. Participants were stakeholders responsible for PDMP implementation in NSW. Recruitment and data collection were completed between March and April 2022. Semi-structured interviews were audio-recorded and transcribed. Two researchers independently reviewed transcripts, generated codes from the data, and mapped these to each NASSS domain. They came together multiple times during data analysis to review the codes and grouped them into higher level themes via a discussion and consensus process. Themes were then organised according to the four objectives of the study. RESULTS: Eight interviews were conducted and analysed after which thematic saturation was reached. All participants had a common understanding of the perceived benefits and drivers for PDMP implementation. Participants outlined ten key ingredients for perceived successful state-wide implementation. Strong and iterative engagement with a large number of stakeholder groups was viewed as critical, as was targeting user experience, ongoing monitoring and evaluation. These were facilitated by a phased roll-out strategy. Participants identified some barriers to implementation, particularly around poor usability and user experience of the tool. CONCLUSIONS: This is one of the first studies focused on strategies for what was perceived to be successful state-wide implementation of PDMP. Successful implementation requires significant time and resourcing, with the design and configuration of the technology being only one component of a multi-strategy process. Knowledge and insights gained from this study may be useful for other implementations of similar digital health tools in large-scale jurisdictions.

Perspectives of Decision Support System TeleRehab in the Management of Post-Stroke Telerehabilitation.

Stroke is the main cause of disability among adults. Decision-making in stroke rehabilitation is increasingly complex; therefore, the use of decision support systems by healthcare providers is becoming a necessity. However, there is a significant lack of software for the management of post-stroke telerehabilitation (TR). This paper presents the results of the developed software "TeleRehab" to support the decision-making of clinicians and healthcare providers in post-stroke TR. We designed a Python-based software with a graphical user interface to manage post-stroke TR. We searched Scopus, ScienceDirect, and PubMed databases to obtain research papers with results of clinical trials for post-stroke TR and to form the knowledge base of the software. The findings show that TeleRehab suggests recommendations for TR to provide practitioners with optimal and real-time support. We observed feasible outcomes of the software based on synthetic data of patients with balance problems, spatial neglect, and upper and lower extremities dysfunctions. Also, the software demonstrated excellent usability and acceptability scores among healthcare professionals.

Generative AI in Critical Care Nephrology: Applications and Future Prospects.

BACKGROUND: Generative artificial intelligence (AI) is rapidly transforming various aspects of healthcare, including critical care nephrology. Large language models (LLMs), a key technology in generative AI, show promise in enhancing patient care, streamlining workflows, and advancing research in this field. SUMMARY: This review analyzes the current applications and future prospects of generative AI in critical care nephrology. Recent studies demonstrate the capabilities of LLMs in diagnostic accuracy, clinical reasoning, and continuous renal replacement therapy (CRRT) alarm troubleshooting. As we enter an era of multiagent models and automation, the integration of generative AI into critical care nephrology holds promise for improving patient care, optimizing clinical processes, and accelerating research. However, careful consideration of ethical implications and continued refinement of these technologies are essential for their responsible implementation in clinical practice. This review explores the current and potential applications of generative AI in nephrology, focusing on clinical decision support, patient education, research, and medical education. Additionally, we examine the challenges and limitations of AI implementation, such as privacy concerns, potential bias, and the necessity for human oversight. KEY MESSAGES: (i) LLMs have shown potential in enhancing diagnostic accuracy, clinical reasoning, and CRRT alarm troubleshooting in critical care nephrology. (ii) Generative AI offers promising applications in patient education, literature review, and academic writing within the field of nephrology. (iii) The integration of AI into electronic health records and clinical workflows presents both opportunities and challenges for improving patient care and research. (iv) Addressing ethical concerns, ensuring data privacy, and maintaining human oversight are crucial for the responsible implementation of AI in critical care nephrology.

An Advanced Machine Learning Model for a Web-Based Artificial Intelligence-Based Clinical Decision Support System Application: Model Development and Validation Study.

BACKGROUND: Breast cancer is a leading global health concern, necessitating advancements in recurrence prediction and management. The development of an artificial intelligence (AI)-based clinical decision support system (AI-CDSS) using ChatGPT addresses this need with the aim of enhancing both prediction accuracy and user accessibility. OBJECTIVE: This study aims to develop and validate an advanced machine learning model for a web-based AI-CDSS application, leveraging the question-and-answer guidance capabilities of ChatGPT to enhance data preprocessing and model development, thereby improving the prediction of breast cancer recurrence. METHODS: This study focused on developing an advanced machine learning model by leveraging data from the Tri-Service General Hospital breast cancer registry of 3577 patients (2004-2016). As a tertiary medical center, it accepts referrals from four branches-3 branches in the northern region and 1 branch on an offshore island in our country-that manage chronic diseases but refer complex surgical cases, including breast cancer, to the main center, enriching our study population's diversity. Model training used patient data from 2004 to 2012, with subsequent validation using data from 2013 to 2016, ensuring comprehensive assessment and robustness of our predictive models. ChatGPT is integral to preprocessing and model development, aiding in hormone receptor categorization, age binning, and one-hot encoding. Techniques such as the synthetic minority oversampling technique address the imbalance of data sets. Various algorithms, including light gradient-boosting machine, gradient boosting, and extreme gradient boosting, were used, and their performance was evaluated using metrics such as the area under the curve, accuracy, sensitivity, and F1-score. RESULTS: The light gradient-boosting machine model demonstrated superior performance, with an area under the curve of 0.80, followed closely by the gradient boosting and extreme gradient boosting models. The web interface of the AI-CDSS tool was effectively tested in clinical decision-making scenarios, proving its use in personalized treatment planning and patient involvement. CONCLUSIONS: The AI-CDSS tool, enhanced by ChatGPT, marks a significant advancement in breast cancer recurrence prediction, offering a more individualized and accessible approach for clinicians and patients. Although promising, further validation in diverse clinical settings is recommended to confirm its efficacy and expand its use.

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.

What Constitutes High Risk for Venous Thromboembolism? Comparing Approaches to Determining an Appropriate Threshold.

Background: Guidelines recommend pharmacological venous thromboembolism (VTE) prophylaxis only for high-risk patients, but the probability of VTE considered "high-risk" is not specified. Our objective was to define an appropriate probability threshold (or range) for VTE risk stratification and corresponding prophylaxis in medical inpatients. Methods: Patients were adults admitted to any of 10 Cleveland Clinic Health System hospitals between December 2020 and August 2021 (N = 41,036). Hospital medicine physicians and internal medicine residents from included hospitals were surveyed between June and November 2023 (N = 214). We compared five approaches to determining a threshold: decision analysis, maximizing the sensitivity and specificity of a logistic regression model, deriving a probability from a point-based model, surveying physicians' understanding of VTE risk, and deriving a probability from physician behavior. For each approach, we determined the probability threshold above which a patient would be considered high-risk for VTE. We applied each threshold to the Cleveland Clinic VTE risk assessment model (CCM) and calculated the percentage of the 41,036 patients in our cohort who would be considered eligible for prophylaxis due to their high-risk status. We compared these hypothetical prophylaxis rates with physicians' observed prophylaxis rates. Results: The different approaches yielded thresholds ranging from 0.3% to 5.4%, corresponding inversely with hypothetical prophylaxis rates of 0.2% to 75%. Multiple thresholds clustered between 0.52% to 0.55%, suggesting an average hypothetical prophylaxis rate of approximately 30%, whereas physicians' observed prophylaxis rates ranged from 48% to 76%. Conclusions: Multiple approaches to determining a probability threshold for VTE prophylaxis converged to suggest an optimal threshold of approximately 0.5%. Other approaches yielded extreme thresholds that are unrealistic for clinical practice. Physicians prescribed prophylaxis much more frequently than the suggested rate of 30%, indicating opportunity to reduce unnecessary prophylaxis. To aid in these efforts, guidelines should explicitly quantify high-risk.

Prediction of COVID-19 Hospitalization and Mortality Using Artificial Intelligence.

BACKGROUND: COVID-19 has had a substantial influence on healthcare systems, requiring early prognosis for innovative therapies and optimal results, especially in individuals with comorbidities. AI systems have been used by healthcare practitioners for investigating, anticipating, and predicting diseases, through means including medication development, clinical trial analysis, and pandemic forecasting. This study proposes the use of AI to predict disease severity in terms of hospital mortality among COVID-19 patients. METHODS: A cross-sectional study was conducted at King Abdulaziz University, Saudi Arabia. Data were cleaned by encoding categorical variables and replacing missing quantitative values with their mean. The outcome variable, hospital mortality, was labeled as death = 0 or survival = 1, with all baseline investigations, clinical symptoms, and laboratory findings used as predictors. Decision trees, SVM, and random forest algorithms were employed. The training process included splitting the data set into training and testing sets, performing 5-fold cross-validation to tune hyperparameters, and evaluating performance on the test set using accuracy. RESULTS: The study assessed the predictive accuracy of outcomes and mortality for COVID-19 patients based on factors such as CRP, LDH, Ferritin, ALP, Bilirubin, D-Dimers, and hospital stay (p-value ≤ 0.05). The analysis revealed that hospital stay, D-Dimers, ALP, Bilirubin, LDH, CRP, and Ferritin significantly influenced hospital mortality (p ≤ 0.0001). The results demonstrated high predictive accuracy, with decision trees achieving 76%, random forest 80%, and support vector machines (SVMs) 82%. CONCLUSIONS: Artificial intelligence is a tool crucial for identifying early coronavirus infections and monitoring patient conditions. It improves treatment consistency and decision-making via the development of algorithms.

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.

The Role of Artificial Intelligence on Tumor Boards: Perspectives from Surgeons, Medical Oncologists and Radiation Oncologists.

The integration of multidisciplinary tumor boards (MTBs) is fundamental in delivering state-of-the-art cancer treatment, facilitating collaborative diagnosis and management by a diverse team of specialists. Despite the clear benefits in personalized patient care and improved outcomes, the increasing burden on MTBs due to rising cancer incidence and financial constraints necessitates innovative solutions. The advent of artificial intelligence (AI) in the medical field offers a promising avenue to support clinical decision-making. This review explores the perspectives of clinicians dedicated to the care of cancer patients-surgeons, medical oncologists, and radiation oncologists-on the application of AI within MTBs. Additionally, it examines the role of AI across various clinical specialties involved in cancer diagnosis and treatment. By analyzing both the potential and the challenges, this study underscores how AI can enhance multidisciplinary discussions and optimize treatment plans. The findings highlight the transformative role that AI may play in refining oncology care and sustaining the efficacy of MTBs amidst growing clinical demands.

Understanding Workflow Nuances That Affect the Use of a Laboratory Test Ordering Support Tool.

The "Emergency Department Pathology Order Support Tool" (ED-POST) is an electronic laboratory test ordering decision support tool that aims to decrease variation in test ordering practices. As part of a larger project on the co-design, development, and evaluation of ED-POST, this study aimed to explore the workflow nuances that might affect the intended use of the digital decision support tool. Semi-structured, in-depth interviews were conducted with 15 ED clinicians involved in the laboratory test ordering process across the development and evaluation phases of ED-POST. Participants identified the expanded role of registered nurses in test ordering and the practice of ordering tests that are outside the ED's scope as contextual characteristics that can affect the use and perceived utility of the proposed ED-POST tool. Reconciling "work-as-imagined" with "work-as-done" in the design and development of electronic interventions is important in achieving interventions to improve the safe and effective use of pathology tests.

A Clinical Decision Support Tool for Intimate Partner Violence Screening Among Women Veterans: Development and Qualitative Evaluation of Provider Perspectives.

BACKGROUND: Women veterans, compared to civilian women, are especially at risk of experiencing intimate partner violence (IPV), pointing to the critical need for IPV screening and intervention in the Veterans Health Administration (VHA). However, implementing paper-based IPV screening and intervention in the VHA has revealed substantial barriers, including health care providers' inadequate IPV training, competing demands, time constraints, and discomfort addressing IPV and making decisions about the appropriate type or level of intervention. OBJECTIVE: This study aimed to address IPV screening implementation barriers and hence developed and tested a novel IPV clinical decision support (CDS) tool for physicians in the Women's Health Clinic (WHC), a primary care clinic within the Veterans Affairs Palo Alto Health Care System. This tool provides intelligent, evidence-based, step-by-step guidance on how to conduct IPV screening and intervention. METHODS: Informed by existing CDS development frameworks, developing the IPV CDS tool prototype involved six steps: (1) identifying the scope of the tool, (2) identifying IPV screening and intervention content, (3) incorporating IPV-related VHA and clinic resources, (4) identifying the tool's components, (5) designing the tool, and (6) conducting initial tool revisions. We obtained preliminary physician feedback on user experience and clinical utility of the CDS tool via the System Usability Scale (SUS) and semistructured interviews with 6 WHC physicians. SUS scores were examined using descriptive statistics. Interviews were analyzed using rapid qualitative analysis to extract actionable feedback to inform design updates and improvements. RESULTS: This study includes a detailed description of the IPV CDS tool. Findings indicated that the tool was generally well received by physicians, who indicated good tool usability (SUS score: mean 77.5, SD 12.75). They found the tool clinically useful, needed in their practice, and feasible to implement in primary care. They emphasized that it increased their confidence in managing patients reporting IPV but expressed concerns regarding its length, workflow integration, flexibility, and specificity of information. Several physicians, for example, found the tool too time consuming when encountering patients at high risk; they suggested multiple uses of the tool (eg, an educational tool for less-experienced health care providers and a checklist for more-experienced health care providers) and including more detailed information (eg, a list of local shelters). CONCLUSIONS: Physician feedback on the IPV CDS tool is encouraging and will be used to improve the tool. This study offers an example of an IPV CDS tool that clinics can adapt to potentially enhance the quality and efficiency of their IPV screening and intervention process. Additional research is needed to determine the tool's clinical utility in improving IPV screening and intervention rates and patient outcomes (eg, increased patient safety, reduced IPV risk, and increased referrals to mental health treatment).