PB0490 Does a Machine Learning Based Algorithm Improve Dosing of Vitamin K Antagonists Compared to Current Decision Support Programs?

The economic and institutional rationale of PV subsidies

Since the 1980s, the number of foreign residents in Japan has continuously been on the rise. In order to improve the foreign resident support services infrastructure and effectiveness, a survey was conducted at a national level from February to August 2002. The survey was done via a mailed questionnaire to all municipalities in Japan. For the purpose of the study, municipalities were divided into four groups based on level of urbanization and numbers of foreign residents in the area. The situation of the foreign maternal and child support programs were compared and the municipal administrations were evaluated. In addition, the attribution analysis and evaluation of the foreigner support program was conducted in each municipality group. The evaluation of the current service support program for foreigner was not judged positively in the majority (95%) of the municipalities. In the non-urbanized municipalities with a low composition of foreigners, the foreigner mother and child support program were not functional compared with other regions. Additionally, various factors were highlighted based on attribution analysis among each group. Although most of the municipalities recognized the importance of the foreign resident support program, the evaluations showed a wide gap between intention and reality. It is recommended that the barriers as identified in the research results are rectified, and the current situation improved based on municipality characteristics, local demands and the needs of the population. The efficient use of limited fiscal and human resources is also advocated by strengthening of cooperation with other official bodies and also employing foreign residents to work in public offices for facilitating the foreign residents support programs.

Background Older informal caregivers are considered to be a growing, vulnerable group with multiple burdens. Existing support programs are rarely used which indicates a lack in meeting the specific demands of the target group. This study was to examine the need for support and the preferred design of support programs for informal caregivers aged 65 years and older. Methods A mixed-methods approach was used to identify types of current support programs and demands regarding health promotion and self-management of older informal caregivers. Therefore, two systematic literature researches and a qualitative survey of German program providers were performed. Furthermore, 16 focus group discussions (FGD) with older informal caregivers as well as three FGD with disseminators in three German cities were accomplished. Results Most support programs found focus on caregiving instead of health promotion. Most FGD participants preferred: social interaction with health promotion activities, programs thematically focusing on relaxation and physical activity as well as consultation meetings. One of the crucial factors of the utilization of support programs is the guaranteed care of the person who requires it simultaneous to an intervention. In general, it was found that informal caregivers prioritize the health of the person in need of care over their own which indicates low self-awareness. Conclusions Support programs combining social interaction with guided health promotion activities seem to be more attractive to informal caregivers than common programs. Those units should especially focus on the low self-awareness the target group shows. Local network structures need to be strengthened to facilitate the development and utilization of support programs. Key messages Networks of disseminators could facilitate support programs for informal caregivers. These programs should contain social interaction, health promotion activities and ensured care of the person who needs it.

Unplanned preventable hospital readmissions within 30 days are a great burden to patients and the healthcare system. With an estimated $41.3 billion spent yearly, reducing such readmission rates is of the utmost importance. With the widespread adoption of big data and machine learning, clinicians can use these analytical tools to understand these complex relationships and find predictive factors that can be generalized to future patients. The object of this study was to assess the efficacy of a machine learning algorithm in the prediction of 30-day hospital readmission after posterior spinal fusion surgery. The authors analyzed the distribution of National Surgical Quality Improvement Program (NSQIP) posterior lumbar fusions from 2011 to 2016 by using machine learning techniques to create a model predictive of hospital readmissions. A deep neural network was trained using 177 unique input variables. The model was trained and tested using cross-validation, in which the data were randomly partitioned into training (n = 17,448 [75%]) and testing (n = 5816 [25%]) data sets. In training, the 17,448 training cases were fed through a series of 7 layers, each with varying degrees of forward and backward communicating nodes (neurons). Mean and median positive predictive values were 78.5% and 78.0%, respectively. Mean and median negative predictive values were both 97%, respectively. Mean and median areas under the curve for the model were 0.812 and 0.810, respectively. The five most heavily weighted inputs were (in order of importance) return to the operating room, septic shock, superficial surgical site infection, sepsis, and being on a ventilator for > 48 hours. Machine learning and artificial intelligence are powerful tools with the ability to improve understanding of predictive metrics in clinical spine surgery. The authors' model was able to predict those patients who would not require readmission. Similarly, the majority of predicted readmissions (up to 60%) were predicted by the model while retaining a 0% false-positive rate. Such findings suggest a possible need for reevaluation of the current Hospital Readmissions Reduction Program penalties in spine surgery.

<b>Background:</b> Around 3-5% of asthma patients are considered severe; if non-responsive to high dose inhaled corticosteroid therapy, these individuals live in fear of experiencing frequent exacerbations which may lead to emergency hospital visits and a severely impaired quality of life (QoL). <b>Aim:</b> The aim was to explore the everyday lives of patients with moderate-severe uncontrolled asthma in order to identify behavioural and physical challenges and uncover how they impact overall QoL. <b>Method:</b> Filmed ethnographic interviews were conducted amongst 20 adult moderate-severe asthma patients across US, UK, France and Germany by a specialist ethnographer in the respondent's native language. <b>Results:</b> It was observed that asthma has both a physical and psychological impact. A broad range of environmental factors and stressful triggers were reported by patients to cause asthmatic exacerbations. The unpredictability of these triggers perpetuated constant feelings of anxiety amongst patients, creating stress and intensifying symptoms. On a physical level, it was observed that severe patients struggle with everyday tasks (e.g. climbing stairs, playing with their children, household chores). Patients try to adapt their lifestyles by avoiding triggers to maintain control and reduce visibility of their disease, but it is often an impossible task. <b>Conclusion:</b> Through understanding the daily struggles faced by a moderate-severe asthma patient, it is possible to identify unmet needs associated with current treatments and support programs within this therapy area.

Feasibility of a real-time hand hygiene notification machine learning system in outpatient clinics

The Internet of things (IoT)-based healthcare decision support system plays a crucial role in modern medicine, especially with the rise in chronic illnesses and an aging population necessitating continuous remote health monitoring. Current healthcare decision support systems struggle to deliver timely and accurate decisions with minimal latency due to limited real-time healthcare data and inefficient computational resources. There is a critical need for an optimized, energy-efficient machine learning model that reliably supports remote health monitoring within IoT and fog computing environments. Our study proposes an Optimized Tiny Machine Learning (TinyML) and Explainable AI (XAI) binary classification model for a trustable and energy-efficient healthcare decision support system, leveraging fog computing to optimize performance. The fog-based approach improves response times and enhances bandwidth usage, addressing critical needs such as reduced latency, higher bandwidth utilization, and decreased packet loss. To further improve efficiency, we incorporate the innovative mLZW data compression technique, significantly enhancing data communication efficiency and reducing response time to critical health alerts. However, limited real-time healthcare data records challenge machine learning classification performance. By implementing a TinyML algorithm, our system demonstrates superior performance to other machine learning models. The proposed optimized TinyML model achieves an impressive F1 score of 0.93 for health abnormalities detection, emphasizing its robustness and effectiveness. This paper highlights the potential of TinyML and XAI in delivering robust, trustworthy, and energy-aware healthcare solutions, making significant contributions toward effective remote health monitoring and decision support in fog-enabled IoT networks.Graphical abstract

3037 Background: Although most cancer can benefit from early detection by more effective treatments and better prognosis, current screening programs are only limited to tumor-specific tests for a subset of common cancers. To benefit a broader population and outweigh the risks of single-cancer tests, an effective and affordable multi-cancer test should be developed for sensitive early detection of multiple cancers and accurate prediction of cancer tissue of origin simultaneously. Methods: In this study, we enrolled 971 cancer patients of the most prevalent and lethal cancer types, including primary liver cancer (PLC, N= 381), colorectal adenocarcinoma (CRC, N= 298), and lung adenocarcinoma (LUAD, N= 292), as well as 243 healthy controls. The participants were randomly divided into a training cohort and a test cohort in a 1:1 ratio. Five fragmentomic features representing cfDNA fragmentation size, motif sequence, and copy number variation were extracted from processed whole-genome sequencing (WGS) data of the participants to build the base models. Each base model implemented five machine learning algorithms for model training, and the optimal base models were used to create the final multi-dimensional model through ensemble stacked machine learning. The integrated multi-cancer model is composed of the first-level binary cancer detection model and the second-level multi-classification cancer origin model. The training cohort was used to train the models with 10-fold cross-validation. The test cohort remained untouched during model construction and was solely used for performance evaluation. Results: Our cancer samples are highlighted by mostly early-stage diseases (early-stage PLC: 88.5%; CRC: 100.0%; LUAD: 100.0%). The cancer detection model reached an area under the curve (AUC) of 0.983 for differentiating cancer patients from healthy individuals in the test cohort. At 95.0% specificity, the sensitivity of detecting all cancer is 95.5%, and 100.0%, 94.6%, and 90.4% for PLC, CRC, and LUAD, respectively. Its sensitivity is consistently high for early-stage, small-size tumors. The cancer origin model demonstrated an overall 93.1% accuracy for predicting tissue of origin in the test cohort (97.4%, 94.3%, and 85.6% for PLC, CRC, and LUAD, respectively). Furthermore, the model's cancer detection and origin classification performance remained robust when reducing sequencing depth to 1× (cancer detection: ≥ 91.5% sensitivity at 95.0% specificity; cancer origin: ≥ 91.6% accuracy). Conclusions: We utilized multiple plasma cfDNA fragmentomic features to build an ensemble stacked machine learning model. The assay reached ultrasensitivity and accuracy for multi-cancer early detection, shedding light on leveraging cfDNA fragmentomics for early screening in clinical practice.

Project proponent- and government-led environmental monitoring are required to identify, understand, and manage cumulative effects (CE), yet such monitoring initiatives are rarely mutually supportive. Notwithstanding the need for a more integrated and complementary approach to monitoring, monitoring efforts are often less effective than intended for addressing CE. This paper examines current monitoring programs in the Mackenzie Valley, Northwest Territories, Canada, based on 7 attributes: consistency, compatibility, observability, detectability, adaptability, accessibility, and usability. Results indicate a tenuous link between and across proponent-led monitoring requirements under project-specific water licenses and government-led monitoring of regional baseline conditions. There is some consistency in what is monitored, but data are often incompatible, insufficient to understand baseline change, not transferable across projects or scales, inaccessible to end users, and ultimately unsuitable to understanding CE. Lessons from the Mackenzie Valley highlight the need for improved alignment of monitoring efforts across programs and scales, characterized by a set of common parameters that are most useful for early detection of cumulative change and supporting regulatory decisions at the project scale. This alignment must be accompanied by more open and accessible data for both proponents and regulators, while protecting the sensitivity of proprietary information. Importantly, there must be conceptual guidance for CE, such that the role of monitoring is clear, providing the types of CE questions to be asked, identifying the hypotheses to be tested, and ensuring timely and meaningful results to support regulatory decisions. © 2019 SETAC.

This special issue is devoted to invited articles on machine learning (ML). Most of the articles included in this issue were also presented in a special session on ML at the 8th International Conference on Human-Compute r Interaction that was held at Yokohama, Japan in July 1995 (Anzai, Ogawa, & Mori, 1995). Since the publication of the first volume of Machine Learning: An Artificial Intelligence Approach (Michalski, Carbonell, & Mitchell, 1983), ML has progressed significantly and several applications have been reported, whereas several others have remained unpublished. In the same volume, the Nobel prize winner Herbert A. Simon places ML in context with learning by stating that learning denotes changes in the system that are adaptive in the sense that they enable the system to do the same task or tasks drawn from the same population more efficiently and more effectively the next time. Many scientific journals and international conferences have hosted special sections and sessions reporting on ML or on applications of ML. Knowledge acquisition, planning, scheduling, decision support, transportation, medicine, and engineering, among others, compose the domains in which ML has been both applied, proved effective, and continues to do so. An attempt to review all ML applications or theory developments would render this introduction or even the special issue endless. In part, a goal of this issue is to extend hands between the two communities: human-computer interaction (HCI) and ML. To a large degree, both share a common goal: Each one tries to improve the human performance and adaptability to changing conditions of some system. Enhancing systems with learning ability may prove conducive to building better systems. Humans come in life with built-in learning potential and excluding artifacts from learning may seriously impede user acceptability of new technology. The article by Moustakis, Lehto, and Salvendy captures expert judgment about a critical question: Which ML method should be used for a given task? The article is based on an extensive survey of ML experts and statistical analysis of responses. It also kicks off the special issue because it briefly introduces the reader to the various ML methods and tasks in which ML may be used. The article by Yoshida and Motoda presents a framework for using ML to automate user modeling and behavior in a user adaptive interface system. It uses

In the past decades, Distribution System Operators (DSOs) have been mitigating distribution networks (DNs) contingencies by opting to grid reinforcements. However, this approach is not always cost and time efficient. Demand Side Flexibility (DSF) is one of the recent alternatives used in DNs congestion management. Consequently, new market players such as aggregators are needed to handle DSF transaction between customers and DSOs. This paper proposes and models a decision support program (DSP) to optimize the total cost charged by the DSO for using DSF services. Moreover, the energy rebound effect is taken into consideration as well as the uncertain behavior of customers. Finally, the distribution grid of the Danish Bornholm Island is used to illustrate the merits of the DSP. The total cost incurred by the DSO is calculated and presented.

Relevance. Monitoring of antibiotic resistance and the frequency of isolation of microorganisms at the regional level in each medical organization is of paramount importance for the implementation of epidemiological safety.Objective. To identify the main microbiological trends based on the analysis of the microflora of patients in a single — profile hospital in order to implement weaknesses in strategic planning activities. Materials and methods. A comprehensive analysis of the pharmacoepidemiological results of the consumption of antimicrobial drugs with calculated drug resistance indices and microbiological monitoring data demonstrated the presence of weaknesses and strengths for the strategic development of a multidisciplinary hospital at the regional level in terms of epidemiological safety. Results. Statistically significant differences in the microbiological structure of pathogens are predetermined by the profile of medical care. The main trends in the change in the microflora of a multidisciplinary hospital as a whole are the prevalence of fungal and gram-negative pathogens over gram-positive ones. The presence of a relatively high index of consumpion of cephalosporins of 3–4 generations, fluoroquinolones, carbapenems, protected penicillins determines the high drug resistance index of Klebsiella pneumoniae (0.86) and characterizes the main microbiological trends of a multidisciplinary clinic. Conclusion. Risk stratification by the level of multidrug-resistant pathogens, the use of deterrent strategies for prescribing antimicrobials, the implementation of educational modules, the evaluation of the effectiveness and monitoring of the risk stratification program with in the framework of antimicrobial technologies, the analysis of microbial landscape data using decision support programs are the main tasks of the functioning of a multidisciplinary team of specialists in a multidisciplinary clinic to control antibiotic resistance.

BackgroundRecently, machine learning (ML) has been transforming our daily lives by enabling intelligent voice assistants, personalized support for purchase decisions, and efficient credit card fraud detection. In addition to its everyday applications, ML holds the potential to improve medicine as well, especially with regard to diagnostics in clinics. In a world characterized by population growth, demographic change, and the global COVID-19 pandemic, ML systems offer the opportunity to make diagnostics more effective and efficient, leading to a high interest of clinics in such systems. However, despite the high potential of ML, only a few ML systems have been deployed in clinics yet, as their adoption process differs significantly from the integration of prior health information technologies given the specific characteristics of ML.ObjectiveThis study aims to explore the factors that influence the adoption process of ML systems for medical diagnostics in clinics to foster the adoption of these systems in clinics. Furthermore, this study provides insight into how these factors can be used to determine the ML maturity score of clinics, which can be applied by practitioners to measure the clinic status quo in the adoption process of ML systems.MethodsTo gain more insight into the adoption process of ML systems for medical diagnostics in clinics, we conducted a qualitative study by interviewing 22 selected medical experts from clinics and their suppliers with profound knowledge in the field of ML. We used a semistructured interview guideline, asked open-ended questions, and transcribed the interviews verbatim. To analyze the transcripts, we first used a content analysis approach based on the health care–specific framework of nonadoption, abandonment, scale-up, spread, and sustainability. Then, we drew on the results of the content analysis to create a maturity model for ML adoption in clinics according to an established development process.ResultsWith the help of the interviews, we were able to identify 13 ML-specific factors that influence the adoption process of ML systems in clinics. We categorized these factors according to 7 domains that form a holistic ML adoption framework for clinics. In addition, we created an applicable maturity model that could help practitioners assess their current state in the ML adoption process.ConclusionsMany clinics still face major problems in adopting ML systems for medical diagnostics; thus, they do not benefit from the potential of these systems. Therefore, both the ML adoption framework and the maturity model for ML systems in clinics can not only guide future research that seeks to explore the promises and challenges associated with ML systems in a medical setting but also be a practical reference point for clinicians.

The purpose of this study is to analyze problematic issues of state planning and management. Based on an analysis of domestic and world experience in project management, it is substantiated that the transition to project management technologies in the form of national priorities and national projects does not allow adequate achievement of planned results. To effectively solve the problem of transforming the economy into an innovative one, general approaches to constructing a new methodology for the formation and implementation of state development programs with a built-in intelligent decision support system are proposed. Methodology. Content, retrospective, comparative analyzes of documents in the field of the state planning system were used; approaches of modern theory of economic systems, information economics and its applied solutions for managing socio-economic systems, methods of economic and mathematical modeling, principles of developing decision support systems, program and project management. The originality /value of the research lies in the development/addition of the theory and methodology of forming a management system for state development programs of the Republic of Kazakhstan in the conditions of transformation of the economy into an innovative one. Findings. Research results. Based on the analysis, a reasoned conclusion is given that Kazakhstan has not developed a systematic view of the system of state planning and management; the applied transition to project management methods, presented in the form of national projects, does not bring the expected results, which may complicate/fail to achieve the goals of state development programs and national projects for the development of a competitive and innovative economy based on the policy of its diversification. The authors make proposals for a scientifically based approach to solving this systemic problem in the form of a new methodology for the formation and implementation of state development programs with a built-in intelligent decision support system.

The model-based Karlsburg Diabetes Management System (KADIS®) has been developed as a personalized decision support (PDS) program to assist physicians in their efforts to achieve optimal metabolic control in each individual patient. For this purpose, KADIS® was evaluated in combination with continuous glucose monitoring (CGM) under different conditions and, last but not least, applied in routine diabetes care. The outcomes of running of PDS for nearly 4 years in routine outpatient diabetes care has convincingly demonstrated that the recommendations provided to the physicians by KADIS® lead to significant improvement of individual metabolic control. It is concluded that this kind of model-based PDS provides an excellent tool to effectively guide physicians in decision making to achieve optimal metabolic control for their patients.