Machine Learning and Artificial Intelligence-Based Clinical Decision Support for Modern Hematology.

Peripheral arterial disease (PAD) is underdiagnosed, partially due to a high prevalence of atypical symptoms and a lack of physician and patient awareness. Implementing clinical decision support tools powered by machine learning algorithms may help physicians identify high-risk patients for diagnostic workup. This study aims to evaluate barriers and facilitators to the implementation of a novel machine learning-based screening tool for PAD among physician and patient stakeholders using the Consolidated Framework for Implementation Research (CFIR). We performed semistructured interviews with physicians and patients from the Stanford University Department of Primary Care and Population Health, Division of Cardiology, and Division of Vascular Medicine. Participants answered questions regarding their perceptions toward machine learning and clinical decision support for PAD detection. Rapid thematic analysis was performed using templates incorporating codes from CFIR constructs. A total of 12 physicians (6 primary care physicians and 6 cardiovascular specialists) and 14 patients were interviewed. Barriers to implementation arose from 6 CFIR constructs: complexity, evidence strength and quality, relative priority, external policies and incentives, knowledge and beliefs about intervention, and individual identification with the organization. Facilitators arose from 5 CFIR constructs: intervention source, relative advantage, learning climate, patient needs and resources, and knowledge and beliefs about intervention. Physicians felt that a machine learning-powered diagnostic tool for PAD would improve patient care but cited limited time and authority in asking patients to undergo additional screening procedures. Patients were interested in having their physicians use this tool but raised concerns about such technologies replacing human decision-making. Patient- and physician-reported barriers toward the implementation of a machine learning-powered PAD diagnostic tool followed four interdependent themes: (1) low familiarity or urgency in detecting PAD; (2) concerns regarding the reliability of machine learning; (3) differential perceptions of responsibility for PAD care among primary care versus specialty physicians; and (4) patient preference for physicians to remain primary interpreters of health care data. Facilitators followed two interdependent themes: (1) enthusiasm for clinical use of the predictive model and (2) willingness to incorporate machine learning into clinical care. Implementation of machine learning-powered diagnostic tools for PAD should leverage provider support while simultaneously educating stakeholders on the importance of early PAD diagnosis. High predictive validity is necessary for machine learning models but not sufficient for implementation.

Personalized asthma management depends on a clinician's ability to efficiently review patient's data and make timely clinical decisions. Unfortunately, efficient and effective review of these data is impeded by the varied format, location, and workflow of data acquisition, storage, and processing in the electronic health record. While machine learning (ML) and clinical decision support tools are well-positioned as potential solutions, the translation of such frameworks requires that barriers to implementation be addressed in the formative research stages. We aimed to use a structured user-centered design approach (double-diamond design framework) to (1) qualitatively explore clinicians' experience with the current asthma management system, (2) identify user requirements to improve algorithm explainability and Asthma Guidance and Prediction System prototype, and (3) identify potential barriers to ML-based clinical decision support system use. At the "discovery" phase, we first shadowed to understand the practice context. Then, semistructured interviews were conducted digitally with 14 clinicians who encountered pediatric asthma patients at 2 outpatient facilities. Participants were asked about their current difficulties in gathering information for patients with pediatric asthma, their expectations of ideal workflows and tools, and suggestions on user-centered interfaces and features. At the "define" phase, a synthesis analysis was conducted to converge key results from interviewees' insights into themes, eventually forming critical "how might we" research questions to guide model development and implementation. We identified user requirements and potential barriers associated with three overarching themes: (1) usability and workflow aspects of the ML system, (2) user expectations and algorithm explainability, and (3) barriers to implementation in context. Even though the responsibilities and workflows vary among different roles, the core asthma-related information and functions they requested were highly cohesive, which allows for a shared information view of the tool. Clinicians hope to perceive the usability of the model with the ability to note patients' high risks and take proactive actions to manage asthma efficiently and effectively. For optimal ML algorithm explainability, requirements included documentation to support the validity of algorithm development and output logic, and a request for increased transparency to build trust and validate how the algorithm arrived at the decision. Acceptability, adoption, and sustainability of the asthma management tool are implementation outcomes that are reliant on the proper design and training as suggested by participants. As part of our comprehensive informatics-based process centered on clinical usability, we approach the problem using a theoretical framework grounded in user experience research leveraging semistructured interviews. Our focus on meeting the needs of the practice with ML technology is emphasized by a user-centered approach to clinician engagement through upstream technology design.

Machine-Learning Implementation in Clinical Anesthesia: Opportunities and Challenges.

Pediatric asthma management via integration of a remote spirometry device into an EHR-based artificial intelligence-powered clinical decision support system: A feasibility pragmatic clinical trial.

Supervised Machine Learning and Clinical Decision Support.

BackgroundEmergency department (ED) providers are important collaborators in preventing falls for older adults because they are often the first health care providers to see a patient after a fall and because at-home falls are often preceded by previous ED visits. Previous work has shown that ED referrals to falls interventions can reduce the risk of an at-home fall by 38%. Screening patients at risk for a fall can be time-consuming and difficult to implement in the ED setting. Machine learning (ML) and clinical decision support (CDS) offer the potential of automating the screening process. However, it remains unclear whether automation of screening and referrals can reduce the risk of future falls among older patients.ObjectiveThe goal of this paper is to describe a research protocol for evaluating the effectiveness of an automated screening and referral intervention. These findings will inform ongoing discussions about the use of ML and artificial intelligence to augment medical decision-making.MethodsTo assess the effectiveness of our program for patients receiving the falls risk intervention, our primary analysis will be to obtain referral completion rates at 3 different EDs. We will use a quasi-experimental design known as a sharp regression discontinuity with regard to intent-to-treat, since the intervention is administered to patients whose risk score falls above a threshold. A conditional logistic regression model will be built to describe 6-month fall risk at each site as a function of the intervention, patient demographics, and risk score. The odds ratio of a return visit for a fall and the 95% CI will be estimated by comparing those identified as high risk by the ML-based CDS (ML-CDS) and those who were not but had a similar risk profile.ResultsThe ML-CDS tool under study has been implemented at 2 of the 3 EDs in our study. As of April 2023, a total of 1326 patient encounters have been flagged for providers, and 339 unique patients have been referred to the mobility and falls clinic. To date, 15% (45/339) of patients have scheduled an appointment with the clinic.ConclusionsThis study seeks to quantify the impact of an ML-CDS intervention on patient behavior and outcomes. Our end-to-end data set allows for a more meaningful analysis of patient outcomes than other studies focused on interim outcomes, and our multisite implementation plan will demonstrate applicability to a broad population and the possibility to adapt the intervention to other EDs and achieve similar results. Our statistical methodology, regression discontinuity design, allows for causal inference from observational data and a staggered implementation strategy allows for the identification of secular trends that could affect causal associations and allow mitigation as necessary.Trial RegistrationClinicalTrials.gov NCT05810064; https://www.clinicaltrials.gov/study/NCT05810064International Registered Report Identifier (IRRID)DERR1-10.2196/48128

In this chapter, we provide a brief overview of applying machine learning techniques for clinical prediction tasks. We begin with a quick introduction to the concepts of machine learning and outline some of the most common machine learning algorithms. Next, we demonstrate how to apply the algorithms with appropriate toolkits to conduct machine learning experiments for clinical prediction tasks. The objectives of this chapter are to (1) understand the basics of machine learning techniques and the reasons behind why they are useful for solving clinical prediction problems, (2) understand the intuition behind some machine learning models, including regression, decision trees, and support vector machines, and (3) understand how to apply these models to clinical prediction problems using publicly available datasets via case studies.

In this paper we discuss the on-going joint work contributing to the IIASA (International Institute for Applied Systems Analysis, Laxenburg, Austria) and National Academy of Science of Ukraine projects on “Modeling and management of dynamic stochastic interdependent systems for food-water-energy-health security nexus” (see [1-2] and references therein). The project develops methodological and modeling tools aiming to create Intelligent multimodel Decision Support System (IDSS) and Platform (IDSP), which can integrate national Food, Water, Energy, Social models with the models operating at the global scale (e.g., IIASA GLOBIOM and MESSAGE), in some cases ‘downscaling’ the results of the latter to a national level. Data harmonization procedures rely on new type non-smooth stochastic optimization and stochastic quasigradient (SQG) [3-4] methods for robust of-line and on-line decisions involving large-scale machine learning and Artificial Intelligence (AI) problems in particular, Deep Learning (DL) including deep neural learning or deep artificial neural network (ANN). Among the methodological aims of the project is the development of “Models’ Linkage” algorithms which are in the core of the IDSS as they enable distributed models’ linkage and data integration into one system on a platform [5-8]. The linkage algorithms solve the problem of linking distributed models, e.g., sectorial and/or regional, into an inter-sectorial inter-regional integrated models. The linkage problem can be viewed as a general endogenous reinforced learning problem of how software agents (models) take decisions in order to maximize the “cumulative reward". Based on novel ideas of systems’ linkage under asymmetric information and other uncertainties, nested strategic-operational and local-global models are being developed and used in combination with, in general, non-Bayesian probabilistic downscaling procedures. In this paper we illustrate the importance of the iterative “learning” solution algorithms based on stochastic quasigradient (SQG) procedures for robust of-line and on-line decisions involving large-scale Machine Learning, Big Data analysis, Distributed Models Linkage, and robust decision-making problems. Advanced robust statistical analysis and machine learning models of, in general, nonstationary stochastic optimization allow to account for potential distributional shifts, heavy tails, and nonstationarities in data streams that can mislead traditional statistical and machine learning models, in particular, deep neural learning or deep artificial neural network (ANN). Proposed models and methods rely on probabilistic and non-probabilistic (explicitly given or simulated) distributions combining measures of chances, experts’ beliefs and similarity measures (for example, compressed form of the kernel estimators). For highly nonconvex models such as the deep ANN network, the SQGs allow to avoid local solutions. In cases of nonstationary data, the SQGs allow for sequential revisions and adaptation of parameters to the changing environment, possibly, based on of-line adaptive simulations. The non-smooth STO approaches and SQG-based iterative solution procedures are illustrated with examples of robust estimation, models’ linkage, machine learning, adaptive Monte Carlo optimization for cat risks (floods, earthquakes, etc.) modeling and management

Machine learning and intelligent decision are important research topics, and the effective combination of the two is a current research hotspot. To further understand the outcomes of the collision of the two fields, this paper comprehensively analyzes the research dynamics of intelligent decision and machine learning from a scientometric perspective using two tools, VOS viewer and CiteSpace. This study provides a holistic insight that helps researchers to better understand the research field. The data analysis of the article is based on 2218 documents retrieved from the Web of Science database from 1990 to 2021. The paper investigates the collaborative network, bibliographic coupling of intelligent decision, and machine learning, revealing the distribution, and closeness of research in the field in terms of countries/regions, institutions, and authors. Further, the paper reveals the research hotspots and research frontiers of the topic through a series of visualization tools such as burst detection. On this basis, the article further discusses the current challenges and possible directions.

It has been reported that the healthcare industry is the slowest adopter of artificial intelligence methods, particularly machine learning (ML), compared to other industries. However, ML can provide unprecedented opportunities for clinical decision-making aid that help improve treatment outcomes and enhance cost-effectiveness. This method paper aims to identify the enablers for adopting ML in supporting clinical decision-making and propose a strategic road map toward boosting the clinicians' intentions to adopt ML as a clinical decision support tool. This paper utilizes the Total Interpretive Structural Modeling (TISM) methodology and the Matrice d'impacts croisés multiplication appliquée á un classment (MICMAC) analysis to investigate the relationships and the interaction between the identified enablers and to develop a hierarchical model that helps policymakers and the other key stakeholders devise the necessary strategies to enhance the adoption of ML in supporting clinical decision-making. The paper concludes that building an academic foundation, raising awareness among the clinicians and patients, building trust in machine learning, and enhancing the perceived normative congruence are among the most important enablers for boosting the clinicians' intentions to adopt machine learning in supporting clinical decision-making.

Construction delays remain a critical challenge globally, significantly affecting project performance metrics such as cost, schedule adherence, quality, and safety. Traditional methods like the Critical Path Method (CPM) and Program Evaluation and Review Technique (PERT) are widely used but lack the predictive capabilities and adaptability required for dynamic project environments. Machine Learning (ML) and Multi-Criteria Decision Analysis (MCDA) have emerged as innovative tools for addressing these limitations. ML excels in predicting delay impacts by analysing historical data and uncovering hidden patterns, while MCDA provides a structured framework for prioritizing delay factors based on their influence on project performance. This paper provides a comprehensive review of the application of ML and MCDA in construction delay management, highlighting their strengths, limitations, and potential integration. The review identifies research gaps, including the need for hybrid frameworks that combine predictive insights with decision support. It proposes future directions to develop real-time tools for delay mitigation, ultimately enhancing construction project outcomes through data-driven decision-making.

Introduction/ Background Medical diagnoses have increasingly depended on digitized images obtained through cutting-edge technology. These algorithms offer a promising avenue to transform diagnostic processes in healthcare, with their application scope continually widening due to ongoing advancements. This paper explores machine learning's role in clinical analysis and prediction, examining various studies that apply these techniques in clinical diagnosis, focusing on their use in analyzing images and providing accurate diagnoses. Materials and Methods This study employs a comparative analysis approach, utilizing diverse machine learning algorithms like SVM, K-nearest neighbors, Random Forests, and Decision Trees to analyze digitized medical images and patient records. We extracted data from several medical databases, ensuring a varied and comprehensive dataset. We also evaluated the impact of different data characteristics on the algorithms' effectiveness, aiming to understand the variability in their diagnostic precision across various conditions. Results The results indicate that machine learning algorithms, particularly SVM, K-nearest neighbors, Random Forests, and Decision Trees, demonstrate significant accuracy in diagnosing diseases from digitized images and medical records. SVM and Random Forests showed particularly high effectiveness in clinical diagnosis, suggesting their robustness across different medical conditions and datasets. These findings underscore the potential of machine learning to enhance diagnostic precision and predict illnesses early, aligning with the growing trend of technology-driven medical diagnostics. Discussion The findings reinforce the pivotal role of machine learning in transforming medical diagnostics. The variability in algorithm performance highlights the necessity for tailored approaches, considering dataset specifics and the medical condition being diagnosed. This study underscores the potential of machine learning to enhance diagnostic accuracy, yet it also emphasizes the need for continuous refinement and understanding of the underlying factors affecting algorithm performance. Future research should focus on optimizing these algorithms within diverse clinical settings to fully harness their diagnostic capabilities. Conclusion This study highlights the transformative potential of machine learning in medical diagnostics, demonstrating how various algorithms can effectively analyze digitized images and patient records to diagnose diseases. While the performance of these algorithms varies based on dataset characteristics, the overall high accuracy underscores machine learning's promise in healthcare. As the field continues to evolve, machine learning is poised to become an integral part of clinical diagnosis, enhancing the accuracy and efficiency of medical evaluations and treatments.

This work proposes a new approach by integrating statistical, machine learning, and multi-criteria decision analysis, including artificial neural network (ANN), logistic regression (LR), frequency ratio (FR), and analytical hierarchy process (AHP). Dependent (flood inventory) and independent variables (flood causative factors) were prepared using remote sensing data and the Mike-11 hydrological model and secondary data from different sources. The flood inventory map was randomly divided into training and testing datasets, where 334 flood locations (70%) were used for training and the remaining 141 locations (30%) were employed for testing. Using the area under the receiver operating curve (AUROC), predictive power of the model was tested. The results revealed that LR model had the highest success rate (81.60%) and prediction rate (86.80%), among others. Furthermore, different combinations of the models were evaluated for flood susceptibility mapping and the best combination (11C) was used for generating a new flood hazard map for Bangladesh. The performance of the 11C integrated models was also evaluated using the AUROC and found that integrated LR-FR model had the highest predictive power with an AUROC value of 88.10%. This study offers a new opportunity to the relevant authority for planning and designing flood control measures.

Melanoma is an aggressive skin cancer associated with a poor prognosis, making survival time a primary concern for patients. This study applies five machine learning models to predict survival rates for melanoma patients, aiming to improve prognostic accuracy and support clinical decision-making. Melanoma patient data were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Five machine learning models-Random Forest, Decision Tree, XGBoost, CatBoost, and LightGBM-were applied to predict 1-year, 3-year, and 5-year survival rates for melanoma patients. The CatBoost model was selected for its superior performance and evaluated using the Area Under the Receiver Operating Characteristic Curve (AUC), confusion matrix, calibration curves, and decision curve analysis (DCA) to assess its accuracy and clinical utility. This study analyzed data from 4,875 patients with cutaneous melanoma, incorporating thirteen demographic and clinical variables to develop survival prediction models using five machine learning algorithms. Among these, the CatBoost model demonstrated the best overall performance and stability following five-fold cross-validation. The model achieved AUC values of 0.7577, 0.7595, and 0.7557 for 1-, 3-, and 5-year survival predictions, respectively. Decision Curve Analysis further confirmed its clinical utility, while consistent precision across both training and test sets indicated robust generalization and reliable predictive capability. These findings highlight the CatBoost model's potential as a practical and accurate tool for assessing melanoma prognosis and supporting individualized clinical decision-making. This model provides clinicians with an effective tool for early intervention, which may ultimately contribute to improved patient survival outcomes.

Employee compliance is a commitment to comply with regulations and stay away from matters that are prohibited in the laws and or company regulations which if not obeyed, then employees are given disciplinary sanctions. Employee discipline is an obligation and willingness of employees in obeying all existing rules in a company to achieve its vision and mission, a high-level employee disciplinary violation rate of 38% at PT. HCI who are engaged in financial service sector can have a negative impact on a company's reputation, meanwhile a low level of employee disciplinary violations in a company can have a positive impact on the company's reputation.This paper aims to predict the possibility of employees committing discipline violations and evaluating the performance of accuracy by using Machine Learning Random Forest, Decision Tree, and Naive Bayes techniques. The test results prove that the Machine Learning Random Forest technique is the best model with the highest value in terms of accuracy with a value of 87.30%, while the Machine Learning Decision Tree and Naive Bayes technique has a value of 83.28%and 70.27% respectively, the value from each of the Machine Learning techniques, the comparison was made using majority voting techniques, so as to produce a total accuracy value of 85.31%.With this high accuracy value, the Random Forest model is proven to have better performance individually in analyzing the prediction of disciplinary violations in the application of human resources at company, while the total accuracy value uses a majority voting model of 85.31%, slightly decreased due to the high level of accuracy of the Naïve Bayes model compared to other algorithm models.