Expert Interpretation Research Articles

The utility of ChatGPT in gender-affirming mastectomy education

IntroductionThe integration of AI such as ChatGPT in medicine has been showing promise in enhancing patient education. Gender-affirming mastectomy (GAM) is a surgical procedure designed to help individuals transition to their self-identified gender, playing a crucial role in mitigating psychological distress for many transmasculine and non-binary (TNB) patients. With increased demand and attention towards GAM, plastic and reconstructive surgeons may rely on AI-driven chatbots as an accessible, accurate, and patient-driven model for relevant details on this procedure. Specific Aim(s)This study aimed to assess the quality and readability of information provided by ChatGPT in response to frequently asked questions (FAQs) related to GAM. MethodsInspired by online forums and physician websites, 10 frequently asked questions (FAQs) about pre- and postoperative topics were submitted to ChatGPT and assessed using validated readability score measures and expert interpretation. ResultsThe average readability score was 16.0 ± 1, indicating a college or graduate reading level. Mean accuracy, comprehensiveness, and danger scores were 8.8 ± 0.5, 7.8 ± 0.7, and 2.2 ± 0.4, respectively. Although physicians appreciated ChatGPT's tone, patient autonomy, and advice to seek professional medical and mental help, they also cited instance of generic information, misinformation, support of debated techniques, and pathologization of gender dysphoria. ConclusionEven with its promise in providing accurate and comprehensive information on GAM, ChatGPT’s current limitations suggest caution as a supplementary tool to physician consultation.

Interpretable Clinical Decision-Making Application for Etiological Diagnosis of Ventricular Tachycardia Based on Machine Learning.

Background: Ventricular tachycardia (VT) can broadly be categorised into ischemic heart disease, non-ischemic structural heart disease, and idiopathic VT. There are few studies related to the application of machine learning for the etiological diagnosis of VT, and the interpretable methods are still in the exploratory stage for clinical decision-making applications. Objectives: The aim is to propose a machine learning model for the etiological diagnosis of VT. Interpretable results based on models are compared with expert knowledge, and interpretable evaluation protocols for clinical decision-making applications are developed. Methods: A total of 1305 VT patient data from 1 January 2013 to 1 September 2023 at the Arrhythmia Centre of Fuwai Hospital were included in the study. Clinical data collected during hospitalisation included demographics, medical history, vital signs, echocardiographic results, and laboratory test outcomes. Results: The XGBoost model demonstrated the best performance in VT etiological diagnosis (precision, recall, and F1 were 88.4%, 88.5%, and 88.4%, respectively). A total of four interpretable machine learning methods applicable to clinical decision-making were evaluated in terms of visualisation, clinical usability, clinical applicability, and efficiency with expert knowledge interpretation. Conclusions: The XGBoost model demonstrated superior performance in the etiological diagnosis of VT, and SHAP and decision tree interpretable methods are more favoured by clinicians for decision-making.

8737 Primary Hyperparathyroidism (PHPT) “Phenotypes” and the Results of Parathyroid [99mTc]Tc-Sestamibi SPECT/CT Scintigraphy: Minimizing the Risk of Negative Imaging Results

Abstract Disclosure: K. Kucharczyk: None. A. Drynda: None. J. Podlewski: None. M. Trofimiuk-Muldner: None. A. Hubalewska-Dydejczyk: None. Introduction. Primary hyperparathyroidism (PHPT) is a prevalent endocrinopathy typically identified through biochemical testing. PHPT is characterized by hypercalcemia accompanied by increased or inappropriately normal plasma parathyroid hormone (PTH) concentrations. Preoperative imaging is conducted when surgery is indicated to pinpoint parathyroid adenomas. [99mTc]Tc-Sestamibi scintigraphy is highly specific and sensitive in diagnosing PHPT, with a higher adenoma detection rate demonstrated for patients with larger lesions or higher blood calcium concentrations. The study aimed to investigate the relationship between the results of biochemical tests and clinical manifestations (PHPT “phenotype”) and the rate of positive results of parathyroid [99mTc]Tc-Sestamibi scintigraphy. Materials and methods. This was a retrospective study of patients suspected of PHPT who underwent parathyroid [99mTc]Tc-Sestamibi SPECT/CT scintigraphy between 2010 and 2022. Patients’ cluster analysis was conducted based on PTH, serum calcium (Ca), and phosphate (Pi) concentrations to find distinct patterns in these parameters. Furthermore, we compared the distributions of additional patients’ attributes, including gender, lesion size, serum vitamin D, ALP concentrations, urinary calcium, urolithiasis prevalence, as well as parathyroid scintigraphy results. Results. 513 patients were divided into 5 clusters using different algorithms. Finally, clusters from K-means methods were selected based on statistical metrics and expert interpretation. Those were organized in ascending order of positive scintigraphy results, with Cluster 5 reaching a 79.5% positivity rate and median values of PTH - 315.5 pmol/L, Ca - 2.96 mmol/L, and Pi - 0.7 mmol/L. As the proportion of positive imaging outcomes declined, median PTH and calcium concentrations decreased while phosphate concentrations increased. In Cluster 1, with 30% of positive imaging results, medians were as follows: PTH - 79.06 pmol/L, Ca - 2.55 mmol/L and Pi - 1.1 mmol/L. A comparative analysis of various clinical and biochemical parameters revealed statistically significant differences between clusters. Patients from Clusters with a higher frequency of positive scintigraphy were significantly more likely to be males, vitamin D deficient, with higher ALP concentrations, diagnosed with urolithiasis, and harbouring larger lesions. Conclusions. PHPT “phenotypes” correlated with disease severity are evidently linked to parathyroid scintigraphy detection rate. Therefore, it is crucial to know that false-negative imaging is more likely in PHPT patients with minor deviations in laboratory tests. Judicious assessment of biochemical and clinical features may limit the number of redundant parathyroid scintigraphies and, in consequence, reduce healthcare costs and unnecessary radiation exposure. Presentation: 6/2/2024

The minimal clinically important difference of two multifaceted fatigue evaluation questionnaires in chronic stroke

ABSTRACT Purpose This research sought to ascertain the Minimal Clinically Important Difference (MCID) and Robust Clinically Important Difference (RCID) of the Multidimensional Fatigue Symptom Inventory-Short Form (MFSI-SF) and Chalder Fatigue Questionnaire-11 (CFQ-11) as two important concepts for the clinical interpretation of the results in chronic post-stroke population. Methods A total of 128 subjects with chronic post-stroke completed the MFSI-SF and CFQ-11 before and after six weeks of intervention. The MCIDs were derived using both anchor- and distribution-based methods; however, only anchor-based methods were used to estimate RCIDs. Results Anchor-based MCIDs for MFSI-SF and CFQ-11 were in the range of −5 to −6.28 and −2 to −4.56, respectively. Distribution-based MCIDs in MFSI-SF and CFQ-11 were calculated in the range of −4.17 to −24.05 and −1.72 to −7.68, respectively. RCID ranges of −10 to −15 were obtained for the MFSI-SF and −6 to −7.33 for the CFQ-11. Conclusion These findings may have implications for clinical experts in the clinical interpretation of fatigue changes observed in MFSI-SF and CFQ-11 in individuals with chronic stroke.

Innovative tools and protocols for the regeneration of urban and peri-urban districts towards climate neutrality

Abstract Cities represent the foremost contributor to the escalating growth in energy consumption, constituting a substantial portion of global greenhouse gas (GHG) emissions. In the face of climate change and the heightened frequency and severity of extreme events, urgent policies and actions are imperative for cities to enhance resilience and instill a sense of responsibility among their inhabitants. Additionally, establishing monitoring and reporting models to track progress in implementing sustainable urban development measures is crucial. The calculation of CO2 emissions in cities demands a multidimensional approach, encompassing sectors such as energy, buildings, water, green spaces, transport, waste, and others. Models and diagnostic tools are available for the different fields of interest. These are valuable elements; however, they often necessitate specialized expertise and prolonged processing times for accurate result interpretation, sometimes conflicting with the need for prompt, reliable guidance. This contribution aims to define innovative tools and protocols, along with a specific performance verification model (easy model), concerning mitigation and adaptation to climate change. These tools are designed to be easy to apply and usable from the preliminary project stages for the redevelopment/regeneration of existing architecture and urban districts.

Using Point of Care Ultrasound (POCUS) to Assess Gastrostomy Balloon Placement

BACKGROUND: Fluoroscopy is the gold-standard for evaluation of gastrostomy tube (GT) placement, though it is costly and resource intensive. Point of Care Ultrasound (POCUS) has potential as a low-risk alternative to confirm GT placement. OBJECTIVE: To determine the diagnostic accuracy of POCUS for identification of correct gastrostomy balloon placement as compared to fluoroscopy. METHODS: This was a prospective convenience sample of children presenting to interventional radiology for routine GT or gastrojejunal (GJ) tube exchange. Prior to exchange, POCUS operators scanned and interpreted ultrasound images for GT placement, followed by fluoroscopy. A blinded radiologist interpreted fluoroscopic studies. Diagnostic test characteristics, concordance with 95% confidence intervals, and interrater agreement (Cohen's Kappa) between POCUS and fluoroscopy were calculated. RESULTS: Four (3%) of 118 evaluated GT balloons were displaced. Compared to fluoroscopy, novice POCUS assessment of GT/GJ balloon placement had a sensitivity of 86% (79-92%), specificity of 25% (1-81%), PPV of 97% (92-99%), NPV of 6% (1-30%), proportion agreement of 85%, kappa 0.04. Expert POCUS interpretation exhibited sensitivity of 91% (89.5%, 100%), proportion agreement of 89%, kappa 0.08. pH testing had the highest sensitivity of 93% (85%, 97%), proportion of agreement (92%) and kappa (0.20). CONCLUSIONS: POCUS demonstrated a high sensitivity for GT/GJ balloon placement, with low interrater agreement with fluoroscopy. POCUS may not add additional clinical benefit in routine evaluation of gastrostomy tubes over current standards of care. However, POCUS may serve as a useful screening test in settings where fluoroscopy is unavailable or pH is unobtainable.

Unsettling the Familiar: Experiential Human Rights Learning through Civic Monuments at the University of Winnipeg

Abstract Research shows that experiential learning improves student learning, engagement and retention and yet, despite growth in university undergraduate human rights programmes, relatively little is known about experiential learning in the human rights classroom. This article examines a low-cost and online-adaptable experiential learning assignment focused on civic statues and monuments in Winnipeg, Canada. The assignment and supporting activities, speakers and resources were implemented in thirteen sections (online and in-person) of a prerequisite-free undergraduate human rights course over two academic years. Surveys were circulated to students before and after the assignment examining their perspective on key concepts and their own skill and capacity. As a result of the activity students indicated a heightened understanding of the role of monuments and representation as human rights issues, a broadened interpretation of expertise in relation to monuments, and an increased self-perception of skills and capacity related to monument analysis. This article contributes to the emerging literature on human rights education in higher education and to the need for accessible, scalable, and online-adaptable forms of experiential learning. Human Rights is a growing field at the undergraduate level, and our project can usefully contribute to the literature and practice of human rights pedagogy.

Deep residual 2D convolutional neural network for cardiovascular disease classification

Cardiovascular disease (CVD) continues to be a major global health concern, underscoring the need for advancements in medical care. The use of electrocardiograms (ECGs) is crucial for diagnosing cardiac conditions. However, the reliance on professional expertise for manual ECG interpretation poses challenges for expanding accessible healthcare, particularly in community hospitals. To address this, there is a growing interest in leveraging automated and AI-driven ECG analysis systems, which can enhance diagnostic accuracy and efficiency, making quality cardiac care more accessible to a broader population. In this study, we implemented a novel deep two-dimensional convolutional neural network (2D-CNN) on a dataset of PTB-XL for cardiac disorder detection. The studies were performed on 2, 5, and 23 classes of cardiovascular diseases. The our network in classifying healthy/sick patients achived an AUC of 95% and an average accuracy of 87.85%. In 5-classes classification, our model achieved an AUC of 93.46% with an average accuracy of 89.87%. In a more complex scenario involving classification into 23 different classes, the model achieved an AUC of 92.18% and an accuracy of 96.88%. According to the experimental results, our model obtained the best classification result compared to the other methods based on the same public dataset. This indicates that our method can aid healthcare professionals in the clinical analysis of ECGs, offering valuable assistance in diagnosing CVD and contributing to the advancement of computer-aided diagnosis technology.

CardiacField: computational echocardiography for automated heart function estimation using two-dimensional echocardiography probes

Abstract Aims Accurate heart function estimation is vital for detecting and monitoring cardiovascular diseases. While two-dimensional echocardiography (2DE) is widely accessible and used, it requires specialized training, is prone to inter-observer variability, and lacks comprehensive three-dimensional (3D) information. We introduce CardiacField, a computational echocardiography system using a 2DE probe for precise, automated left ventricular (LV) and right ventricular (RV) ejection fraction (EF) estimations, which is especially easy to use for non-cardiovascular healthcare practitioners. We assess the system’s usability among novice users and evaluate its performance against expert interpretations and advanced deep learning (DL) tools. Methods and results We developed an implicit neural representation network to reconstruct a 3D cardiac volume from sequential multi-view 2DE images, followed by automatic segmentation of LV and RV areas to calculate volume sizes and EF values. Our study involved 127 patients to assess EF estimation accuracy against expert readings and two-dimensional (2D) video-based DL models. A subset of 56 patients was utilized to evaluate image quality and 3D accuracy and another 50 to test usability by novice users and across various ultrasound machines. CardiacField generated a 3D heart from 2D echocardiograms with <2 min processing time. The LVEF predicted by our method had a mean absolute error (MAE) of 2.48%, while the RVEF had an MAE of 2.65%. Conclusion Employing a straightforward apical ring scan with a cost-effective 2DE probe, our method achieves a level of EF accuracy for assessing LV and RV function that is comparable to that of three-dimensional echocardiography probes.

Review article: Recommendations for detection, assessment and management of suspected drug‐induced liver injury during clinical trials in oncology patients

SummaryBackgroundDrug‐induced liver injury (DILI) is a major concern for oncology drugs in clinical practice and under development. Monitoring cancer patients for hepatotoxicity is challenging as these patients may have abnormal liver tests pre‐treatment or on‐study for many reasons including liver injury due to past oncology treatments, hepatic metastases, medical co‐morbidities such as heart failure, and concomitant medications. At present, there are no regulatory guidelines or position papers that systematically address best practices pertaining to DILI detection, assessment and management in oncology patients.AimsThe goals of this review are (1) to examine and interpret the available evidence and (2) to make recommendations for detection, monitoring, adjudication, and management of suspected hepatocellular DILI during oncology clinical trials.MethodsThis manuscript was developed by the IQ Consortium (International Consortium for Innovation and Quality in pharmaceutical development) DILI Initiative that consists of members from 17 pharmaceutical companies, in collaboration with academic and regulatory DILI experts. The manuscript is based on extensive literature review, expert interpretation of the literature, and several rounds of consensus discussions.ResultsThis review highlights recommendations for patient eligibility for clinical trials with or without primary/metastatic liver involvement, as well as changes in liver tests that should trigger increased monitoring and/or discontinuation of study drug. Guidance regarding causality assessment for suspected DILI events, rechallenge and dose‐modification is provided.ConclusionsThis review brings together evidence‐based recommendations and expert opinion to provide the first dedicated consensus for best practices in detection, assessment, and management of DILI in oncology clinical trials.

Parathyroid gland identification and angiography classification using simple machine learning methods.

Near-infrared indocyanine green angiography allows experienced surgeons to reliably evaluate parathyroid gland vitality during thyroid and parathyroid operations in order to predict postoperative function. To facilitate equal performance between surgeons, we developed an automatic computational quantification method using computer vision that portrays expert interpretation of visualized parathyroid gland near-infrared indocyanine green angiographic fluorescence signals. Near-infrared indocyanine green-parathyroid gland angiography video recordings (Fluobeam® LX, Fluoptics, Grenoble-part of Getinge-Göteborg) from patients undergoing endocrine cervical surgery in a high-volume unit were used for model development. Computation (MATLAB, Mathworks, Ireland) included segmentation-identification of the parathyroid gland (by autofluorescence), image stabilization (by linear translation) and adjusted time-fluorescence intensity profile generation. Relative upslope and maximum intensity ratios then trained a simple logistic regression model based on expert interpretation and outcome (including hypoparathyroidism), with subsequent unseen testing for validation. The model was trained on 37 patient videos (45 glands, 29 judged well perfused by parathyroid gland angiography experts), achieving feature data separation with 100% accuracy, and tested on 22 unseen videos (27 glands, 15 judged well perfused), including four in real time. Segmentation-guided parathyroid gland detection correctly identified all parathyroid glands during unseen testing along with three additional non-parathyroid gland regions (90% positive predictive value). Subsequent time-fluorescence intensity profile extraction with vitality prediction was shown feasible in all cases within 5 min, with a 96.3% model accuracy (sensitivity and specificity were 93.3 and 100% respectively) when compared with expert judgement. Automatic parathyroid gland perfusion quantification using simple machine learning computational methods discriminates parathyroid gland perfusion in concordance with expert surgeon interpretation, providing a means for near-infrared indocyanine green-parathyroid gland signal evaluation.

Specifications of the ACMG/AMP variant curation guidelines for the analysis of germline ATM sequence variants.

The ClinGen Hereditary Breast, Ovarian, and Pancreatic Cancer (HBOP) Variant Curation Expert Panel (VCEP) is composed of internationally recognized experts in clinical genetics, molecular biology, and variant interpretation. This VCEP made specifications for the American College of Medical Genetics and Association for Molecular Pathology (ACMG/AMP) guidelines for the ataxia telangiectasia mutated (ATM) gene according to the ClinGen protocol. These gene-specific rules for ATM were modified from the ACMG/AMP guidelines and were tested against 33 ATM variants of various types and classifications in a pilot curation phase. The pilot revealed a majority agreement between the HBOP VCEP classifications and the ClinVar-deposited classifications. Six pilot variants had conflicting interpretations in ClinVar, and re-evaluation with the VCEP's ATM-specific rules resulted in four that were classified as benign, one as likely pathogenic, and one as a variant of uncertain significance (VUS) by the VCEP, improving the certainty of interpretations in the public domain. Overall, 28 of the 33 pilot variants were not VUS, leading to an 85% classification rate. The ClinGen-approved, modified rules demonstrated value for improved interpretation of variants in ATM.

A novel algorithm developed using machine learning and a J-ACCESS database can estimate defect scores from myocardial perfusion single-photon emission tomography images.

Stress myocardial perfusion single-photon emission computed tomography (SPECT) imaging (MPI) has been used to diagnose and predict the prognoses of patients with coronary artery disease (CAD). An ongoing multicenter collaboration established a Japanese database (J-ACCESS) in 2001 that includes a risk model and expert interpretations. The present study aimed to develop a novel algorithm using machine learning (ML) and resources from the J-ACCESS database to aid SPECT image interpretation. We analyzed data from 1288 patients in J-ACCESS 3 and 4 databases. Three-dimensional (3D) stereoscopic images of left ventricular myocardial perfusion were reconstructed with linear transformation from the original short-axis data. Segments were extracted from U-Net, then features were extracted from each segment during the ML process. We estimated segmental scores based on weighted features obtained from fully connected layers. Correlations between segment scores interpreted by nuclear cardiology experts and estimated by ML were evaluated using a 17-segment model, summed stress (SSS), summed rest (SRS), and summed difference (SDS) scores, and ratios (%) of summed different scores (%SDS). The complete concordance rate of scores assessed by the experts and estimated by ML was 79.6%. The underestimated and overestimated rates were 10.3% and 10.0%, respectively. Associations between defect scores assessed by experts and ML were close, with correlation coefficients (r) of 0.923, 0.917, 0.842 and 0.853 for SSS, SRS, SDS, %SDS, respectively (p < 0.0001 for all). We created a new algorithm to estimate MPI scores using ML and the J-ACCESS database. This algorithm should provide accurate MPI interpretation even in facilities without specialist nuclear cardiologists, and might facilitate therapeutic decision-making and predict prognoses.

Direct immunofluorescence demystified: Essential insights and recent advances for dermatologists.

Direct immunofluorescence (DIF) is widely used in dermatopathology for the diagnosis of autoimmune blistering diseases (AIBDs), cutaneous vasculitis, and connective tissue disorders. Although it is easy and useful to perform, it needs technical expertise and experience for proper interpretation. The yield of DIF depends on multiple factors including the adequacy, transportation, storage, processing, and interpretation of the biopsy specimen. Effective collaboration between the dermatologist and dermatopathologist along with meticulous clinico-pathological correlation is crucial for accurately interpreting DIF in the appropriate clinical context. In this narrative review of DIF in dermatology, we discuss the indications of DIF, recent updates on the selection of optimum biopsy sites, basic techniques of DIF including the classical transport medium and its alternatives, processing and staining technique, patterns in various diseases, advancements such as serration pattern analysis, and latest recommendations on the use of DIF in cutaneous disorders.

Deep learning approaches for the detection of scar presence from cine cardiac magnetic resonance adding derived parametric images.

This work proposes a convolutional neural network (CNN) that utilizes different combinations of parametric images computed from cine cardiac magnetic resonance (CMR) images, to classify each slice for possible myocardial scar tissue presence. The CNN performance comparison in respectto expert interpretation of CMR with late gadolinium enhancement (LGE) images, used as ground truth (GT), was conducted on 206 patients (158 scar, 48 control) from Centro Cardiologico Monzino (Milan, Italy) at both slice- and patient-levels. Left ventricle dynamic features were extracted in non-enhanced cine images using parametric images based on both Fourier and monogenic signal analyses. The CNN, fed with cine images and Fourier-based parametric images, achieved an area under the ROC curve of 0.86 (accuracy 0.79, F1 0.81, sensitivity 0.9, specificity 0.65, and negative (NPV) and positive (PPV) predictive values 0.83 and 0.77, respectively), for individual slice classification. Remarkably, it exhibited 1.0 prediction accuracy (F1 0.98, sensitivity 1.0, specificity 0.9, NPV 1.0, and PPV 0.97) in patient classification as a control or pathologic. The proposed approach represents a first step towards scar detection in contrast-free CMR images. Patient-level results suggest its preliminary potential as a screening tool to guide decisions regarding LGE-CMR prescription, particularly in cases where indication is uncertain.

Evaluating machine learning techniques for enhanced glaucoma screening through Pupillary Light Reflex analysis

Glaucoma is a leading cause of irreversible visual field degradation, significantly impacting ocular health. Timely identification and diagnosis of this condition are critical to prevent vision loss. A range of diagnostic techniques is employed to achieve this, from traditional methods reliant on expert interpretation to modern, fully computerized diagnostic approaches. The integration of computerized systems designed for the early detection and classification of clinical indicators of glaucoma holds immense potential to enhance the accuracy of disease diagnosis. Pupillary Light Reflex (PLR) analysis emerges as a promising avenue for glaucoma screening, mainly due to its cost-effectiveness compared to exams such as Optical Coherence Tomography (OCT), Humphrey Field Analyzer (HFA), and fundoscopic examinations. The noninvasive nature of PLR testing obviates the need for disposable components and agents for pupil dilation. This facilitates multiple successive administrations of the test and enables the possibility of remote execution. This study aimed to improve the automated diagnosis of glaucoma using PLR data, conducting an extensive comparative analysis incorporating neural networks and machine learning techniques. It also compared the performance of different data processing methods, including filtering techniques, feature extraction, data balancing, feature selection, and their effects on classification. The findings offer insights and guidelines for future methodologies in glaucoma screening utilizing pupillary light response signals.

Precision and Robust Models on Healthcare Institution Federated Learning for Predicting HCC on Portal Venous CT Images.

Hepatocellular carcinoma (HCC), the most common type of liver cancer, poses significant challenges in detection and diagnosis. Medical imaging, especially computed tomography (CT), is pivotal in non-invasively identifying this disease, requiring substantial expertise for interpretation. This research introduces an innovative strategy that integrates two-dimensional (2D) and three-dimensional (3D) deep learning models within a federated learning (FL) framework for precise segmentation of liver and tumor regions in medical images. The study utilized 131 CT scans from the Liver Tumor Segmentation (LiTS) challenge and demonstrated the superior efficiency and accuracy of the proposed Hybrid-ResUNet model with a Dice score of 0.9433 and an AUC of 0.9965 compared to ResNet and EfficientNet models. This FL approach is beneficial for conducting large-scale clinical trials while safeguarding patient privacy across healthcare settings. It facilitates active engagement in problem-solving, data collection, model development, and refinement. The study also addresses data imbalances in the FL context, showing resilience and highlighting local models' robust performance. Future research will concentrate on refining federated learning algorithms and their incorporation into the continuous implementation and deployment (CI/CD) processes in AI system operations, emphasizing the dynamic involvement of clients. We recommend a collaborative human-AI endeavor to enhance feature extraction and knowledge transfer. These improvements are intended to boost equitable and efficient data collaboration across various sectors in practical scenarios, offering a crucial guide for forthcoming research in medical AI.

Artificial intelligence and electrocardiography: A modern approach to heart rate monitoring

The integration of Artificial Intelligence (AI) in Electrocardiography (ECG) and Photoplethysmography (PPG) signifies AI's profound influence on heart rate monitoring and analysis. ECG traditionally offers critical insights into cardiac health, necessitating expert interpretation. This study introduces an AI framework with Fast Fourier Transformation Analysis for swift, human-like interpretation of complex ECG signals. A multilayer AI Network accurately detects intricate features, enhancing ECG analysis precision. Leveraging comprehensive datasets, AI models proficiently identify heart dysfunctions like atrial fibrillation and hypertrophic cardiomyopathy, and can estimate age, sex, and race. The proliferation of mobile ECG technologies has spurred AI-based ECG phenotyping, impacting clinical and population health. This research explores AI's role in enhancing cardiac health assessment and clinical decision-making using MATLAB, acknowledging its transformative potential and inherent limitations.

Assessing knowledge gaps and educational needs in urine drug test interpretation among health care professionals.

Urine drug testing (UDT) is a critical tool used in medical, forensic, and occupational settings, but interpreting results can be challenging. We performed a study to assess the ability of health care professionals to interpret UDT results accurately. In total, 911 clinical and laboratory professionals in the United States and Canada responded to a survey with questions gauging expertise in UDT interpretation. Responses were analyzed to identify knowledge gaps. Toxicologists and laboratory PhD scientists performed well, with means of 4.82 and 4.63 questions answered correctly (out of 6 possible), respectively. Physicians specializing in pathology, emergency medicine, primary care, and internal medicine, however, displayed concerning knowledge gaps, as did laboratorians with nondoctoral degrees. Experience and training correlated with interpretation accuracy. Identification of simulated compliance as well as understanding opioid exposure, metabolism, and immunoassay cross-reactivity were among the most clinicallysignificant knowledge gaps. More than 30% of survey respondents indicated that they would seek UDT information from the internet or peers rather than clinical or laboratory experts. The study highlighted the need for targeted education and better collaboration between clinical and laboratory experts and other health care professionals to ensure that when physicians order UDT, they can accurately interpret results and reduce harm.

Podnebne projekcije temperature zraka in padavin za porečja Ledave, Pesnice in Vipave do konca 21. stoletja

As part of the project ‚CeVoTak‘, Integrated Management of Small Water Retention and Soil Erosion Prevention Measures in Agricultural Catchments, we studied changing temperature and precipitation conditions up to the year 2100. The study was conducted on agricultural lands in the catchments of the Ledava and Pesnica rivers in the sub-Pannonian region and the Vipava river in the sub-Mediterranean region. A common climate database was used to create the climate projections - RCM (Regional Climate Model) simulations from the project EURO-CORDEX and scenarios RCP (Representative Concentration Pathway), RCP2.6, 4.5 and 8.5. The projections were prepared for three time periods 2011-2040; 2041-2070 and 2071-2100 for 6 different regional climate models for average, minimum and maximum air temperatures and precipitation. Analysis of the ensemble of model simulations for all scenarios shows similar results for the basin of all rivers, an increase in temperature (maximum in winter, minimum in spring), with high confidence for all scenarios and periods. Projections of precipitation are less reliable, but show an increase in annual precipitation due to the winter increase. The use of climate change projections with expert interpretation is essential for determining the vulnerability of individual areas and building resilience through the implementation of climate change adaptation.