Support Tool Research Articles

Large language models as a diagnostic support tool in neuropathology.

The WHO guidelines for classifying central nervous system (CNS) tumours are changing considerably with each release. The classification of CNS tumours is uniquely complex among most other solid tumours as it incorporates not just morphology, but also genetic and epigenetic features. Keeping current with these changes across medical fields can be challenging, even for clinical specialists. Large language models (LLMs) have demonstrated their ability to parse and process complex medical text, but their utility in neuro-oncology has not been systematically tested. We hypothesised that LLMs can effectively diagnose neuro-oncology cases from free-text histopathology reports according to the latest WHO guidelines. To test this hypothesis, we evaluated the performance of ChatGPT-4o, Claude-3.5-sonnet, and Llama3 across 30 challenging neuropathology cases, which each presented a complex mix of morphological and genetic information relevant to the diagnosis. Furthermore, we integrated these models with the latest WHO guidelines through Retrieval-Augmented Generation (RAG) and again assessed their diagnostic accuracy. Our data show that LLMs equipped with RAG, but not without RAG, can accurately diagnose the neuropathological tumour subtype in 90% of the tested cases. This study lays the groundwork for a new generation of computational tools that can assist neuropathologists in their daily reporting practice.

Value-based optimization model for cultural route design: Ancient Water Supply Heritage of Istanbul (Türkiye)

Cultural tourism has become an increasingly growing human activity in today's world. Therefore, various cultural/natural heritage areas or buildings face large tourist crowds, causing physical, social, or cultural deterioration. Cultural routes, which provide a systematic approach and planned tourists move, can reduce the negative effects of overtourism. This study aims to develop an optimization model as a supportive tool for the cultural route design process. The proposed optimization model aims to maximize cultural experience while satisfying constraints on heritage values, building types, historical eras, and general routing rules. Moreover, this model, creating optimized cultural routes, is expected to contribute to regulating economic income and tourist density. As a case study, the ancient water supply systems of Istanbul, inherited from the Roman and the Ottoman empires and currently overlooked, are investigated. Heritage values, mentioned in the extensive literature, are reviewed and the values/attributes for this study are appointed according to the characteristics of the case heritage assets, and their environment. The values of the case structures are evaluated with value analysis after field study. An optimum cultural route for Istanbul's historical water supply heritage, according to the objective and the constraints of the model, is obtained by solving the model with the case data. The resulting route can make this overlooked heritage of Istanbul recognized and spread the tourist density in the city center. The model is flexible, allowing for easy modification of the objective function, constraints, and values when designing routes across various heritage sites. This model can be used not only in the design of new cultural routes but also in optimizing existing routes.

Where to plan shared streets: Development and application of a multicriteria spatial decision support tool

In response to the growing recognition of the vital role played by streets as public spaces in enhancing the vibrancy of urban life, various concepts aiming at creating greener and more inclusive streets have gained popularity in recent years, especially in North America. Shared streets are one example of such concepts that have attracted the attention of citizens and of urban and transportation planning professionals alike. This was the case in the city of Sherbrooke (Quebec, Canada) where, in response to numerous citizens’ requests, a need was identified to develop decision aid tools to help evaluate and rank street segments based on their potential to become shared streets. To achieve this, an action-research project was initiated in which we conducted a socio-technical process based on MACBETH, a multicriteria evaluation method. The project led to the development of a spatial decision support tool, operationally used today by the city professionals. This tool ensures a more informed and transparent decision-making process and supports shared streets planning policy. The methods developed are generalizable and can be adapted to other cities facing similar planning problems.

Clean energy challenges and innovation opportunities in Kazakhstan

Abstract Kazakhstan has pledged to transition to a low-carbon economy by implementing national policies and strategies that promote clean energy innovation. However, Kazakhstan is still falling short of its expected targets for energy transition, and there is a lack of knowledge regarding the country’s challenges and opportunities for clean energy development. Towards this end, the current study identifies and assesses the enablers and barriers related to clean energy innovation in Kazakhstan. Using the combination of SWOT analysis, survey data from 41 experts and the DEMATEL decision support tool, we evaluated the key factors affecting Kazakhstan’s clean energy innovation and their implications for energy transition. Assessment results show that the immature business environment, underpinned by technological, institutional, and socioeconomic factors, is perceived as a high-impact constraint for clean energy innovation and green finance deployment in Kazakhstan. Skilled labour shortages, high reliance on hydrocarbons and low retail energy prices are significant challenges to Kazakhstan’s clean energy innovation. The low-profit margin and high investment risk in clean energy projects are identified as transition barriers in the power and energy-intensive industries. In contrast, Kazakhstan’s endowments of resources critical for developing clean energy technologies (rare earth metals, uranium, gas) and the potential of low-carbon investments (e.g. carbon storage) are perceived as prominent enablers of clean energy innovation. Results are consistent across expert subgroups (academia, industry, NGOs, etc). Findings call for policy support to modern and attractive business environments, capacity, and human capital development. The findings can provide helpful insights for countries in Central Asia and beyond with similar socioeconomic structures that aim for a timely energy transition.

30-day Spirometry Holter method design and prospective observational study

Asthma underdiagnosis and overdiagnosis remain significant problems for healthcare systems worldwide and indicate considerable pain points with current guidelines and diagnostic methods; therefore, new, targeted approaches seem crucial. This study introduces a novel spirometry-based approach using digital tools for objective asthma diagnosis support. This was a single-centre (Warsaw Medical University, Poland) prospective cohort study. It included adults with suspected asthma per GINA 2020, without confirmed obstruction in ambulatory spirometry. Patients were equipped and trained with a portable spirometer with built-in manoeuvre quality features AioCare® (HealthUp, Poland). The protocol included twice-daily spirometry examinations over four weeks and symptom reporting in the mobile app. The number of obstructions detected, probability of finding obstruction over time, spirometry values’ variability, technical correctness, and reported symptoms were evaluated. 26 patients enrolled (14 females, mean age 37.6 years old, BMI 24.7 kg/m^2), with a primary outcome of observed obstruction in 42% of participants (3.08 per patient, 95%CI: 0.78–5.37). The detection probability of obstruction plateaued at 100% within the first 21 days of monitoring. Diurnal PEF and FEV1 variability were exceeded (≥ 10%) in 73% and 66% of patients, respectively. 88% of participants performed over half of their tests correctly. 85% of patients reported symptoms at least once. The Spirometry Holter is a novel and feasible tool for monitoring airway limitation variability in line with GINA guidelines. It shows promise in objectively supporting asthma diagnoses in treatment-naive patients lacking documented prior obstruction.

Economic considerations of in‐season potassium applications to soybean using payoff matrices

AbstractPotassium (K) deficiency is a common yield‐limiting factor in Arkansas soybean (Glycine max (L.) Merr.) production that can be addressed with innovative supplemental fertilizer application. An established leaf sampling protocol and dynamic critical concentration allow accurate diagnosis of K deficiency with corresponding recommendations for corrective, in‐season K fertilizer applications at site‐specific rates and times to reach anticipated yield goals. However, the profitability of in‐season K fertilizer applications to irrigated soybean remains unclear. Research was conducted in Arkansas from 2021 to 2023 to evaluate multiple rates of in‐season applications of muriate of potash to soybean at 15 and 30 days after first flower (DAR1). The economic ramifications of in‐season fertilizer applications were quantified by calculating yield averages, partial returns (PRs), and regret when comparing PR to not fertilizing, each assuming 5‐year average prices for fertilizer and soybean grain. Significant yield responses to in‐season potash fertilizer were found at both 15 and 30 DAR1 times. These yield increases translated to large increases in PR or lower regret when compared to using no fertilizer. Corrective applications of 74–112 kg K ha−1 were often considered optimal, with risk assessments provided to allow informed decisions. Results were summarized by category of leaf‐K concentration, and treatment averages were provided to calculate payoff matrices for 15 and 30 DAR1 times. The resulting payoff matrices can be used as a decision support tool with any grain and fertilizer price to facilitate informed management decisions that optimize profitability as soybean and fertilizer prices impact optimal outcomes.

Improving peripheral artery disease screening and treatment: a screening, diagnosis, and treatment tool for use across multiple care settings.

Peripheral artery disease (PAD) is an atherosclerotic disease that contributes to significant morbidity and mortality, including loss of limb, myocardial infarction (MI), stroke, and death. Treatment options are often underutilized. A major limiting factor in PAD care is the ability to efficiently identify and screen at-risk patients. A PAD patient screening and clinician decision support tool was created to improve access to high-quality, evidence-based care to drive improved clinical outcomes. The tool identifies known PAD risk factors and presenting symptoms, in combination with objective data obtained via the ankle-brachial index (ABI). The tool utilizes this data to drive PAD diagnosis, risk assessment, and treatment, and it is adaptable across multiple care settings, by varied health professions. The implementation of a PAD screening and treatment toolkit enhances anticoagulation and PAD stewardship, and it has been integrated into use across various care settings.

Health Care Professionals' Experience of Using AI: Systematic Review With Narrative Synthesis.

There has been a substantial increase in the development of artificial intelligence (AI) tools for clinical decision support. Historically, these were mostly knowledge-based systems, but recent advances include non-knowledge-based systems using some form of machine learning. The ability of health care professionals to trust technology and understand how it benefits patients or improves care delivery is known to be important for their adoption of that technology. For non-knowledge-based AI tools for clinical decision support, these issues are poorly understood. The aim of this study is to qualitatively synthesize evidence on the experiences of health care professionals in routinely using non-knowledge-based AI tools to support their clinical decision-making. In June 2023, we searched 4 electronic databases, MEDLINE, Embase, CINAHL, and Web of Science, with no language or date limit. We also contacted relevant experts and searched reference lists of the included studies. We included studies of any design that reported the experiences of health care professionals using non-knowledge-based systems for clinical decision support in their work settings. We completed double independent quality assessment for all included studies using the Mixed Methods Appraisal Tool. We used a theoretically informed thematic approach to synthesize the findings. After screening 7552 titles and 182 full-text articles, we included 25 studies conducted in 9 different countries. Most of the included studies were qualitative (n=13), and the remaining were quantitative (n=9) and mixed methods (n=3). Overall, we identified 7 themes: health care professionals' understanding of AI applications, level of trust and confidence in AI tools, judging the value added by AI, data availability and limitations of AI, time and competing priorities, concern about governance, and collaboration to facilitate the implementation and use of AI. The most frequently occurring are the first 3 themes. For example, many studies reported that health care professionals were concerned about not understanding the AI outputs or the rationale behind them. There were issues with confidence in the accuracy of the AI applications and their recommendations. Some health care professionals believed that AI provided added value and improved decision-making, and some reported that it only served as a confirmation of their clinical judgment, while others did not find it useful at all. Our review identified several important issues documented in various studies on health care professionals' use of AI tools in real-world health care settings. Opinions of health care professionals regarding the added value of AI tools for supporting clinical decision-making varied widely, and many professionals had concerns about their understanding of and trust in this technology. The findings of this review emphasize the need for concerted efforts to optimize the integration of AI tools in real-world health care settings. PROSPERO CRD42022336359; https://tinyurl.com/2yunvkmb.

EXPERIENCE OF IMPLEMENTING THE DISTANCE E-COURSE “STATISTICAL METHODS IN PHARMACY” IN THE MATHEMATICAL TRAINING OF FUTURE PHARMACEUTICAL SPECIALISTS

The article is dedicated to the issue of distance and online learning in higher pharmaceutical education. In the paper, the main principles and characteristic features of the concept of distance learning are outlined, the main advantages and disadvantages of using distance and e-learning in pharmaceutical and medical higher education are discussed. Considerable attention is paid to the use of distance learning technology in the process of math training for students pursuing higher education in the field of pharmacy. In addition to technical means and the structural-methodological component of the distance course development process, special attention is given to psycho-pedagogical aspects, which includes a focus on increasing the motivation of this group of education seekers to master disciplines related to exact sciences. It is demonstrated, using the example of the developed by the authors distance course “Statistical Methods in Pharmacy”, implemented with the LMS Moodle, that a successful combination of methodological approaches and innovative teaching methods, aimed at implementing a competency-based approach in education, along with modern information technology providing online access to educational content, including tools for feedback support, practical skills development, and automated self-assessment, ensures the effectiveness of achieving educational goals by learners and the formation of professional competencies defined by the educational program. The course was tested, certified, and implemented in the fundamental training of future pharmaceutical professionals at the National University of Pharmacy. It is concluded, that the implementation of distance learning technology in the practice of Ukrainian higher pharmaceutical and medical education is necessary not only due to the current conditions that make it impossible to organize full-fledged offline education but also because of the efficiency of these technologies, primarily for organizing independent students’ work, that ensures the development of learners’ autonomy, contributes to the development of information culture, general digital competence, and a range of soft skills, including communication, interaction, collaboration in a digital environment, and the rational use of study time.

SPICT tool among intubated elderly patients at emergency department

BackgroundThe global rise in the aging population necessitates a proactive approach to palliative care, with a substantial gap between the demand for and access to such care. The Supportive and Palliative Care Indicators Tool (SPICT) has emerged as a valuable instrument for identifying patients at risk of deterioration and death, enhancing the timely initiation of palliative care. This study aimed to investigate the characteristics and outcomes of patients aged 60 and above who got intubated in the emergency department (ED), with and without fulfilling SPICT criteria. MethodsThis retrospective single-center study was conducted at a tertiary care teaching hospital in Thailand. The research involved 408 adults aged 60 and older who underwent ED intubation and subsequent admission. Baseline characteristics and follow-up data were collected, encompassing vital signs, comorbidities, and SPICT criteria. Mortality rates between SPICT criteria-fulfilled and non-fulfilled groups were compared. ResultsOut of 408 analyzed patients, SPICT criteria were met by 39.7 % of patients, exhibiting distinctive features such as a higher respiratory rate and lower diastolic blood pressure. Hypertension and diabetes mellitus were most prevalent comorbidities. Respiratory and neurological disorders were the leading final diagnoses. The overall in-hospital mortality rate was 28 %, significantly higher in the SPICT criteria-fulfilled group compared to the non-fulfilled group (34.0 % vs 23.6 %, P = 0.022). SPICT criteria demonstrated moderate sensitivity (48.7 %) and specificity (63.7 %) for predicting mortality. ConclusionSPICT criteria identified elderly patients at an elevated mortality risk following intubation in the emergency setting. The early implementation of SPICT as a screening tool for identifying palliative care candidates is advocated for more effective advance care planning.

Machine learning techniques for diagnosis of rare diseases from medical images

Introduction/Background: Rare diseases are life-threatening or chronically debilitating conditions that affect a small percentage of the population. Early and accurate diagnosis of rare diseases is challenging due to their complexity and limited understanding. Conventional diagnostic methods are often inadequate, time-consuming, and expensive. Machine learning (ML) has emerged as a promising technique for the analysis of medical images to support the diagnosis of various diseases including rare disorders. ML algorithms can learn complex patterns from large medical imaging datasets to aid clinicians in disease diagnosis, prognosis, and detection of complications. Materials and Methods: A structured search was conducted in electronic databases, including PubMed, Scopus, Web of Science, and Google Scholar to identify peer-reviewed articles published between 2013 to 2023 related to ML-based diagnosis of rare diseases from medical images. A total of 187 articles were identified after removing duplicates. The titles and abstracts of retrieved articles were screened to determine their relevance based on the research objective. Finally, 51 full-text articles were selected for the final review. The key data extracted from selected studies included diseases, imaging modalities, ML algorithms, performance metrics, datasets, and limitations. Results: Most studies evaluated deep learning-based ML techniques, with convolutional neural networks (CNN) being the most applied algorithm. CNNs were mainly used to classify rare diseases based on specific imaging features in X-rays, CT, and MRI scans. Diseases frequently investigated included cardiovascular, neurological, and rare genetic disorders. Publicly available datasets such as Deep Lesion, MSD, and ChestX-ray14 were commonly utilized. Most studies reported high classification accuracy ranging from 80-95% on test datasets. However, limited generalizability due to small private datasets and lack of external validation were limitations. Discussion: The results demonstrate the potential of deep learning for the image-based diagnosis of rare diseases. Features learned from large imaging data sets enabled CNNs to distinguish subtle abnormalities. Hybrid models combining CNNs with other techniques like recurrent neural networks further improved performance. Overall, ML showed promise as a decision support tool. However, more multi-center validation studies are needed using larger and diverse datasets before clinical adoption. Standardization of performance metrics and reporting is also required to establish reliability and generalizability. Conclusion: This comprehensive review provided insights into ongoing research applying ML to medical images for rare disease diagnosis. While initial results are encouraging, further work is still necessary before ML can be reliably used in clinical decision making. Larger collaborative efforts and open-source datasets are needed to advance the field. Standardization of ML frameworks can also promote reproducible research and comparison of different methodologies.

Right Information, Right Care, Right Patient, Right Time: Community Preferences to Inform a Self-Management Support Tool for Upper Respiratory Symptoms.

During and after the COVID-19 pandemic, communities must cope with several conditions that cause similar upper-respiratory symptoms but are managed differently. We describe community reactions to a self-management toolkit for patients with upper respiratory symptoms to inform mobile e-health app development. The toolkit is based on the '4R' (Right Information, Right Care, Right Patient, Right Time) care planning and management model. The 4R Cold, Flu and COVID-19 Information Tool (4R-Toolkit) along with a brief evaluation survey were distributed in three ways: through a Bronx NY Allergy/Asthma clinic, through the Bronx Borough President's Office listserv, and through peer recruitment. The survey assessed respondents' perceptions of the 4R-Toolkit's accessibility, preferences for sharing symptoms with clinicians, social media use, and e-health literacy. We obtained a diverse sample of 106 Bronx residents, with 83% reporting personal or a social contact with symptoms suggestive of COVID-19. Respondents varied in the information sources they preferred: computer (39%); smart phone (28%); paper (11%) and no preference (22%). Most (67%) reported that social media had at least some impact on their healthcare decisions. Regardless of media preferences, respondents were positive about the 4R-Toolkit. Out of 106 respondents, 91% believed the 4R-Toolkit would help people self-manage upper respiratory symptoms and 85% found it easy to understand. Respondents strongly endorsed retention of all 4R-Toolkit content domains with 81% indicating that they would be willing to share symptoms with providers using a 4R-Toolkit smartphone app. The 4R-Toolkit can offer patients and community members accurate and up-to-date information on COVID-19, the common cold, and the flu. The user-friendly tool is accessible to diverse individuals, including those with limited e-health literacy. It has potential to support self-management of upper respiratory symptoms and promote patient engagement with providers.

Integration and Evaluation of a Digital Support Function for Space Claims in Factory Layout Planning

Planning and designing factory layouts are frequently performed within virtual environments, relying on inputs from various cross-disciplinary activities e.g., product development, manufacturing process planning, resource descriptions, ergonomics, and safety. The success of this process heavily relies on the expertise of the practitioners performing the task. Studies have shown that layout planning often hinges on the practitioners’ knowledge and interpretation of current rules and requirements. As there is significant variability in this knowledge and interpretation, there is a risk that decisions are made on incorrect grounds. Consequently, the layout planning process depends on individual proficiency. In alignment with Industry 4.0 and Industry 5.0 principles, there is a growing emphasis on providing practitioners involved in industrial development processes with efficient decision support tools. This paper presents a digital support function integrated into a virtual layout planning tool, developed to support practitioners in considering current rules and requirements for space claims in the layout planning process. This digital support function was evaluated by industry practitioners and stakeholders involved in the factory layout planning process. This initiative forms part of a broader strategy to provide advanced digital support to layout planners, enhancing objectivity and efficiency in the layout planning process while bridging cross-disciplinary gaps.

How Are Weather and Climate Products and Decision Support Systems Used in Wildland Fire Decision Making in the US Southwest?

Abstract Wildland fire management is a challenging environment in which to utilize scientific information. Despite the robust information system that supports US wildland fire management, recent studies demonstrate that some data/information products and decision support tools available to that community are not being used to their full potential. In the US Southwest the convergence of climate change, past wildland fire policy, and an expanding wildland urban interface has increased pressure on wildland fire managers to use science-based information to improve management outcomes. This tension between the perceived need for more science in fire management and the practical challenges of using science to inform decisions led us to ask two basic questions: 1) How is information about weather and climate used in wildland fire management decision making in the Southwest? 2) How are decision support tools used in Southwest wildland fire management? We found: relatively few sources of weather and climate information are consulted by Southwest wildland fire managers; a small percentage of those sources are used to inform the specific decisions and tasks we asked about; decision support tools are commonly used to justify rather than inform decisions. We further found evidence that suggests that products and tools that are thoughtfully designed to fit within the specific information use environment of wildland fire management—rather than being produced in isolation from that environment—are more likely to be used and therefore have more impact than those that are produced in isolation from that environment.

Investigation on chatter stability of thin-walled parts milling considering the effects of fixture support force and tool position

The chatter stability of thin-walled parts milling has garnered widespread attention in recent years, leading to numerous important findings. However, the effects of tool position and the fixture support force applied to the workpiece on the chatter stability have yet to be adequately studied. Therefore, this paper aims to explore the mechanisms by which these two factors affect the chatter stability of thin-walled parts milling. First, based on the structural characteristics of the milling system, a three-degree-of-freedom dynamic model for thin-walled parts milling is developed. Subsequently, modal impact tests are conducted to obtain the dynamic parameters under different fixture support forces and tool positions, and the evolution of these dynamic parameters under different fixture support forces and tool positions is explored in depth. Next, the semi-discrete method is employed to solve the dynamic model, analyzing the effects of fixture support force and tool position on the chatter stability of thin-walled parts milling. Finally, milling experiments are carried out to validate the accuracy of the model. The experimental results indicate that the stability prediction results from the established dynamic model are in agreement with the experimental results, demonstrating its effectiveness in assessing the chatter stability of thin-walled parts milling.

Transfer learning classification of suspicious lesions on breast ultrasound: is there room to avoid biopsies of benign lesions?

BackgroundBreast cancer (BC) is the most common malignancy in women and the second cause of cancer death. In recent years, there has been a strong development in artificial intelligence (AI) applications in medical imaging for several tasks. Our aim was to evaluate the potential of transfer learning with convolutional neural networks (CNNs) in discriminating suspicious breast lesions on ultrasound images.MethodsTransfer learning performances of five different CNNs (Inception V3, Xception, Densenet121, VGG 16, and ResNet50) were evaluated on a public and on an institutional dataset (526 and 392 images, respectively), customizing the top layers for the specific task. Institutional images were contoured by an expert radiologist and processed to feed the CNNs for training and testing. Postimaging biopsies were used as a reference standard for classification. The area under the receiver operating curve (AUROC) was used to assess diagnostic performance.ResultsNetworks performed very well on the public dataset (AUROC 0.938–0.996). The direct generalization to the institutional dataset resulted in lower performances (max AUROC 0.676); however, when tested on BI-RADS 3 and BI-RADS 5 only, results were improved (max AUROC 0.792). Good results were achieved on the institutional dataset (AUROC 0.759–0.818) and, when selecting a threshold of 2% for classification, a sensitivity of 0.983 was obtained for three of five CNNs, with the potential to spare biopsy in 15.3%–18.6% of patients.ConclusionIn conclusion, transfer learning with CNNs may achieve high sensitivity and might be used as a support tool in managing suspicious breast lesions on ultrasound images.Relevance statementTransfer learning is a powerful technique to exploit the performances of well-trained CNNs for image classification. In a clinical scenario, it might be useful for the management of suspicious breast lesions on breast ultrasound, potentially sparing biopsy in a non-negligible number of patients.Key PointsProperly trained CNNs with transfer learning are highly effective in differentiating benign and malignant lesions on breast ultrasound.Setting clinical thresholds increased sensitivity.CNNs might be useful as support tools in managing suspicious lesions on breast ultrasound.Graphical

Health information system assessments: Opportunities for international collaboration

Abstract Since the late 1990s, with the development of European Core Health Indicators (ECHI) and the European Health Interview Survey (EHIS), the EU aims to strengthen its continental database for evidence-informed public health policy and research. BRIDGE Health (2015-2017), InfAct (Information for Action 2018-2021) and PHIRI (Population Health Information Research Infrastructure 2020-2023) projects prepared for the establishment of a sustainable European health information infrastructure. Country health information system (HIS) assessments were core project activities, performed on the basis of the WHO Euro ‘Support Tool to strengthen health information systems’. To serve project objectives, the original top-down Support Tool was modified and implemented in a peer-to-peer approach among project countries. InfAct and PHIRI conducted 9 country peer-assessments each. InfAct assessments were carried out through country visits, targeting overall health information inequalities and good practices. PHIRI performed virtual country visits, focusing on COVID-19 health information flows. The WHO Tool was further adapted by the Joint Action TEHDAS (2021-2023) to assess the readiness of HIS in Europe for the European Health Data Space. Experience with these different iterations led to the revision of the Support Tool in 2021 to include a more expanded and modular approach which enables HIS assessments to opt to focus on specific aspects. To date, a sustainable European health information infrastructure has not been set up. Currently, the EU funds a joint Health Information Network with WHO Euro. Building regional infrastructures for public health and NCDI/MH monitoring and reporting depend on structures and on the political will of supranational organizations and their members. Meanwhile, HIS assessments to improve surveillance, population health and to reduce health information inequalities lend themselves to increased international collaboration and knowledge exchange.

Pharmacologic treatment of hypertension guided by non-invasive haemodynamics in primary care improves blood pressure control

Abstract Background Current guidelines on hypertension (HTN) provide blood pressure (BP) targets and therapeutic algorithms but ignore the potential to treat individual patients according to their haemodynamic profile. We have shown that use of non-invasive haemodynamic information obtained by impedance cardiography (ICG) can improve BP control in the primary care setting. Purpose To investigate whether improved rates of BP control by matching patients’ non-invasive haemodynamics to specific pharmacologic treatments and increasing patient engagement translates into improved clinical outcome measures. Methods Electronic medical records (EMR) were obtained for 14,698 patients from two US primary care groups between 2014 and 2023. ICG was done when BP exceeded 140/90 mmHg. Haemodynamic measurements included mean arterial pressure (MAP), cardiac index (CI), cardiac power index (CPI), total peripheral resistance index (TPRI), stroke index (SI) and heart rate (HR) (Figure 1). Haemodynamic ICG profiles were classified as: Vasoconstriction, Hyperdynamic, or Mixed pattern. Printed clinical decision support (CDS) tools and later an EMR integrated CDS application were used to communicate recommendations to physicians. Printed reports were shared with patients to increase their engagement. Pharmacological therapy was tailored based on haemodynamic information. Rates of successful BP treatment and the occurrence of myocardial infarction (MI) or stroke were tracked through the EMR. Results Of 14,698 patients, 50% were women, 17% were Black and 17% were aged 18-49 years, 45% aged 50-69 years, and 38% age ≥ 70 years. A total of 21,246 ICGs were performed classifying patients as Vasoconstriction 47%, Hyperdynamic with high heart rate (HR) or high stroke index (SI) 24%, and Mixed Haemodynamic (combination of Vasoconstriction and Hyperdynamic) 29% (Figure 1). Demographic features were not strongly associated with haemodynamic classification. Within 2-3 years of inclusion, >85% of patient achieved BP control (<140/90 mmHg), which was sustained during follow-up. Over a median (IQR) follow-up of 8 (2016-2023) years, there were 14 (5) MI and 34 (16) strokes. These event rates appear to be lower than those reported in other large cohorts of patients with HTN. Conclusions Treating patients with HTN according to their individual haemodynamic profile is associated with high rates of BP control. Further analysis will determine whether the rates of MI, stroke and death are lower than expected based on the patients baseline risk profile.Haemodynamic Status (ICG Test Results)

Rasch model of teacher readiness instrument for implementing science learning based on Balinese local wisdom

Local culture has undergone significant shifts and alienations, leading to the neglect of societal values. This situation underscores the need for teachers to be well-prepared to incorporate local wisdom into science education, supporting Cultured-Based Learning. This study, conducted from January to June 2022, aimed to assess the relevance of items in a teacher readiness instrument for implementing local wisdom-based science learning in Bali. An ex post facto research design was employed to analyze the preparedness of 72 science teachers in Bali through a detailed questionnaire. The collected ordinal data were converted into an interval scale using the Method of Successive Interval (MSI) and analyzed using the Rasch Model with the Jamovi application to assess item relevance. The study's findings highlight the cognitive and emotional readiness of science teachers as being in the high category, while collegial support and instructional tools are in the low category. These results suggest that improving collegial features and instructional tools through lesson studies and workshops could enhance the integration of local wisdom into science education in Bali.

Concordance between cardiological interventions and artificial intelligence recommendations for patients presenting with chest pain, based on consultations from the emergency department to cardiology

Abstract Introduction The management of chest pain in emergency departments is a critical challenge. The integration of advanced artificial intelligence (AI) tools, such as pre-trained generative systems like ChatGPT, may present an opportunity to optimize this diagnostic process. This study investigates the effectiveness of AI in recommending diagnostic tests for patients presenting with chest pain, evaluating its concordance with clinical decisions by experienced cardiologists. Methods Retrospective observational study where 102 cases of patients with chest pain treated in the ED and assessed by Cardiology between January and March 2023 were reviewed. Chest pain was classified into high, medium and low probability. Data from emergency department to cardiology consultations were presented to ChatGPT, asking which diagnostic test it would recommend: conventional ergometry, coronary CT, imaging stress test, coronary angiography, or discharge. Various concordance indices, such as Simple Match and Tanimoto, among others, were used to evaluate the consensus between ChatGPT recommendations and cardiologists' decisions (table 2). Results Out of the 102 cases collected, 54% presented with high, 35% with medium and 11% with low probability chest pain. Table 1 summarizes the different proposals between the cardiologist and the AI. For patients with high probability chest pain, coronary angiography was the most commonly requested test, with a positive concordance of 77% according to the Simple Match index and 72% as per the Tanimoto coefficient. For other tests such as ergometry or imaging stress test, there were a 77% and 74% agreement, respectively, in not performing these tests, and there was an almost unanimous agreement (close to 100%) against discharging patients without conducting tests. Medium probability chest pain was more frequent and complex in its management. The decision to perform a coronary angiography agreed in 70% according to the Simple Match index and 72% with Tanimoto. The decision not to discharge patients directly without conducting tests showed a higher agreement at 89%. Other results were less precise. For low probability chest pain, there was a notable concordance (90%) in the decision not to perform diagnostic tests, such as imaging stress test, according to the Simple Match index. Conclusions - The AI achieves a notable concordance with cardiologists' decisions in the diagnostic approach of chest pain, particularly for patients with high probability chest pain, where the coronary angiography demonstrated good agreement. - Although AI cannot fully replace the clinical judgment of cardiologists in cases based on self-reported information, its utility as a supportive tool underscores the potential for its careful integration with medical expertise to enhance the diagnostic process. This implies the need for the development of specialized AI tools to better assist cardiologists in patient diagnosis.Table 1Table 2